Water treatment equipment management method and system based on Internet of Things

Abstract

The invention discloses a water treatment equipment management method and system based on the Internet of Things, relates to the technical field of intelligent data processing and analysis, and is used for solving the problem of poor equipment detection effect. The method comprises the following steps: firstly, collecting water treatment equipment state and surrounding water area water body condition data, and dividing the data into a plurality of sub-areas; and implementing different data acquisition schemes in each sub-region. Through data cleaning and analysis, a high-division area and a low-division area are determined, so that different equipment and water body monitoring strategies are formulated. And after fusing the multi-source data, performing state prediction and fusion by adopting Kalman filtering and a graph neural network, and finally generating a health index of the water treatment equipment. Key parameters of the equipment are adjusted in real time based on the health index, and faults are avoided. The method has the functions of accurate equipment state monitoring, intelligent adjustment and efficient fault prevention, and the stability and management efficiency of the water treatment equipment can be remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent data processing and analysis technology, and more specifically, to a water treatment equipment management method and system based on the Internet of Things. Background Technology

[0002] With the rapid development of the water treatment industry, water treatment equipment is increasingly widely used in various water treatment projects, especially in urban water supply, sewage treatment, and water quality monitoring. Traditional water treatment equipment management typically relies on manual inspections and periodic maintenance, which suffers from insufficient real-time monitoring, untimely fault warnings, and low operating efficiency. Furthermore, the water treatment process is affected by various environmental factors and equipment performance, making it difficult to detect changes in equipment status in a timely manner, leading to frequent equipment failures and increased maintenance costs.

[0003] To improve the management efficiency of water treatment equipment and reduce operational risks, an increasing number of intelligent technologies are being applied to the monitoring and management of water treatment equipment. Intelligent water treatment equipment management systems based on Internet of Things (IoT) technology are becoming a trend. These systems use sensor networks to monitor the equipment's operating status and water quality in real time, and combine data analysis with artificial intelligence algorithms to intelligently predict and optimize equipment adjustments. However, current systems generally suffer from insufficient data processing accuracy, poor environmental adaptability, and a lack of sufficient real-time performance and reliability in their intelligent algorithms, and have not yet fully achieved intelligent management and fault prevention for water treatment equipment.

[0004] To address the above problems, this invention proposes a solution. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a water treatment equipment management method and system based on the Internet of Things to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: In a preferred embodiment, it includes: Step 1: Divide the water treatment equipment and the surrounding water area into multiple sub-regions for the water treatment equipment and sub-regions for the water area, and collect data for each sub-region accordingly; Step 2: Screen for areas that can be integrated and determine the health index of the current water treatment equipment; Step 3: Adjust the key parameters of the water treatment equipment in real time based on the current health index of the water treatment equipment; Step 4: Build a remote visual management and monitoring system for water treatment equipment with early warning capabilities.

[0007] In a preferred embodiment, in step 1, the water treatment equipment and the water area surrounding the water treatment equipment are physically divided into uniform or non-uniform sections. Data on the fluid shear force distribution and corrosion potential distribution of the water treatment equipment surface in each water treatment equipment sub-region are collected. The weighted average of these data is used to determine the equipment area score Fs for each sub-region. The equipment area score Fs of each sub-region is then compared with the equipment score threshold Ys. When the equipment area score Fs of a sub-region is greater than or equal to the equipment score threshold Ys, it indicates that the sub-region belongs to a high-scoring equipment area. When the equipment area score Fs of a sub-region is less than the equipment score threshold Ys, it indicates that the sub-region belongs to a low-scoring equipment area.

[0008] In a preferred embodiment, in step 1, hydrodynamic turbulence intensity and microbial diversity index data are collected in each water sub-region. The weighted average of the quantified values ​​of hydrodynamic turbulence intensity and microbial diversity index determines the water score Sy for each water sub-region. The water score Sy of each water sub-region is compared with the water score threshold Ysy. When the water score Sy of a water sub-region is greater than or equal to the water score threshold Ysy, it indicates that the water sub-region is a low-pollution water area. When the water score Sy of a water sub-region is less than the water score threshold Ysy, it indicates that the water sub-region is a high-pollution water area.

[0009] In a preferred embodiment, in step 1, the overlapping portion of the highly polluted water area and the low-pollution water area is determined and denoted as the neutralized water area. The dissolved oxygen concentration data of the water in the neutralized water area is calculated, and a dissolved oxygen threshold Yr is set. When the dissolved oxygen concentration data of the neutralized water area is greater than or equal to the dissolved oxygen threshold Yr, the sampling scheme of the low-pollution water area should be adopted; when the dissolved oxygen concentration data of the neutralized water area is less than the dissolved oxygen threshold Yr, the sampling scheme of the highly polluted water area should be adopted.

[0010] In a preferred embodiment, in step 2, the distribution data of fluid shear force on the surface of the water treatment equipment and corrosion potential of the water treatment equipment material in the water treatment equipment sub-region, as well as the DTW distance of the hydrodynamic turbulence intensity and microbial diversity index quantification values ​​in the water area sub-region, are calculated and weighted to determine the final weighted distance value D. When D is less than or equal to the fusion threshold Yz, the sub-region is considered to be a fusionable region. When D is greater than the fusion threshold Yz, the sub-region is considered to be a non-fusionable region.

[0011] In a preferred embodiment, in step 2, multi-source data from the water treatment equipment sub-region and the water area sub-region within the fusionable region are fused.

[0012] In a preferred embodiment, in step 2, the Pearson correlation coefficient and Spearman rank correlation coefficient of the equipment data and water area data are calculated, and strongly correlated equipment data Bs and water area data Ys are selected; the health index of the water treatment equipment is calculated.

[0013] In a preferred embodiment, in step 3, the key parameters of the water treatment equipment are dynamically adjusted based on the health index of the water treatment equipment obtained in step 2.

[0014] In a preferred embodiment, in step 4, the water treatment equipment is equipped with network connectivity to build an Internet of Things (IoT) access system for the water treatment equipment; and hierarchical alarms are set.

[0015] In a preferred embodiment, the device score threshold Ys is obtained as follows; The mean, standard deviation, median, and quartiles of the fluid shear force distribution on the surface of the water treatment equipment and the corrosion potential distribution of the materials of the water treatment equipment were calculated. K-means clustering was used for analysis to determine the equipment score threshold Ys.

[0016] In a preferred embodiment, the module includes: a data acquisition module, a status analysis and health assessment module, a parameter intelligent control module, a GIS module, and a remote monitoring and early warning module, with signal connections between each module; The GIS module is mainly used to generate detailed geographic information maps of water bodies by combining the FVCOM water flow simulation model; The data acquisition module is mainly used to divide the area into sub-regions, deploy sensors according to risk level, and collect data in real time. The status analysis and health assessment module is mainly used to screen water areas that can be integrated, integrate multiple types of data, calculate the health index of water treatment equipment, and determine the operational risks of water treatment equipment. The intelligent parameter control module is mainly based on the equipment health index and automatically adjusts parameters such as water pump and chemical dosage to prevent malfunctions and optimize efficiency. The remote monitoring and early warning module is mainly used for real-time data display via network connection, and pushes alarms in a tiered manner when anomalies occur, thereby realizing remote management.

[0017] The technical effects and advantages of the water treatment equipment management method and system based on the Internet of Things of this invention are as follows: This invention achieves adaptive control of key parameters by dynamically monitoring the status of water treatment equipment and aquatic environment data in different regions, combining multi-source data fusion and intelligent algorithms to generate equipment health indices. Its advantages lie in accurately identifying equipment risk areas and the degree of water pollution, significantly improving equipment operational stability and fault prevention capabilities through a tiered early warning mechanism and remote visual management, while optimizing resource allocation efficiency and reducing operation and maintenance costs, providing an intelligent and systematic solution for water treatment equipment management. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the structure of a water treatment equipment management system based on the Internet of Things according to the present invention.

[0019] Figure 2 This is an operation flowchart of a water treatment equipment management method based on the Internet of Things according to the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Example

[0021] This invention discloses a water treatment equipment management method based on the Internet of Things, such as... Figure 2 As shown, it includes: Step 1: Divide the water treatment equipment into multiple sub-regions and collect data for each sub-region accordingly.

[0022] The water treatment equipment to be tested and the water area around the water treatment equipment are physically divided into multiple sub-regions. Based on the different regional characteristics of each sub-region of the water treatment equipment or the water area around the water treatment equipment, different data collection schemes for water conditions or water treatment equipment status are selected in different sub-regions. The sensors for collecting data are connected in each sub-region through a wireless sensor network. The specific steps for dividing water treatment equipment into sub-regions and collecting water treatment equipment status data are as follows: A 3D mesh model of the water treatment equipment was constructed using the finite element method (FEM) to define the boundaries of the entire water treatment equipment and to uniformly divide the surface of the entire water treatment equipment into multiple sub-regions. Since the fluid shear force on the surface of water treatment equipment affects scale deposition, biofilm formation, and material wear rate, deposits are less likely to form in high-shear-force areas, while scale easily accumulates in low-shear-force areas. Therefore, for each sub-region of the water treatment equipment, miniature thermal film shear force sensors are installed on the surface of the water treatment equipment to measure the shear force distribution data when the fluid flows across the surface of the water treatment equipment and output it in real time. Then, computational fluid dynamics (CFD) simulation is used in conjunction with the measured shear force data, and the fluid shear force distribution on the surface of the water treatment equipment is calculated using the finite element method (FEM). At the same time, considering that the corrosion potential determines the corrosion rate on the surface of the water treatment equipment, and the corrosion potential difference at different locations leads to electrochemical corrosion, scanning vibration electrode technology (SVET) based on micro-area electrode corrosion potential measurement is further used to place electrodes at different locations on the water treatment equipment to measure the corrosion potential distribution at different locations on the surface of the water treatment equipment and obtain the corrosion potential distribution data of the water treatment equipment material. Then, electrochemical noise analysis (EN) is used to calculate the corrosion potential gradient and plot the corrosion potential distribution map.

[0023] Furthermore, mathematical or empirical formulas are used to normalize the data on the fluid shear force distribution on the surface of the water treatment equipment and the corrosion potential distribution of the materials in the water treatment equipment, converting them into quantitative values. The specific formulas used are as follows: In the formula, Normalized_Score is the normalized value; then, the weighted average of the quantified values ​​of the fluid shear force distribution on the surface of the water treatment equipment and the corrosion potential distribution data of the water treatment equipment materials determines the equipment area score Fs for each water treatment equipment sub-region, specifically according to the formula: Fs=Q1×Jq+Q2×Fd, where Q1 represents the weight of the quantified value of the fluid shear force distribution data on the surface of the water treatment equipment, Jq represents the quantified value of the fluid shear force distribution data on the surface of the water treatment equipment, Q2 represents the weight of the quantified value of the quantified value of the corrosion potential distribution data of the water treatment equipment materials, and Fd represents the quantified value of the corrosion potential distribution data of the water treatment equipment materials.

[0024] Next, the collected data on the distribution of fluid shear force on the surface of the water treatment equipment and the distribution of corrosion potential of the water treatment equipment materials were cleaned using the Pandas library to remove missing and duplicate data, generating a clean and complete dataset. The mean, standard deviation, median, and quartiles of the data on the distribution of fluid shear force on the surface of the water treatment equipment and the distribution of corrosion potential of the water treatment equipment materials were calculated. K-means clustering was used for analysis to determine the equipment score threshold Ys. The equipment region score Fs of each water treatment equipment sub-region was compared with the equipment score threshold Ys. When the equipment region score Fs of a water treatment equipment sub-region is greater than or equal to the equipment score threshold Ys, it indicates that the water treatment equipment sub-region belongs to the high-scoring equipment region; when the equipment region score Fs of a water treatment equipment sub-region is less than the equipment score threshold Ys, it indicates that the water treatment equipment sub-region belongs to the low-scoring equipment region. The following is the data collection scheme for the equipment status data of the high-resolution equipment area: By employing multi-sensor fusion to enhance the accuracy of equipment status detection, FPGAs or edge computing nodes are deployed on water treatment equipment in high-resolution equipment areas, and ultrasonic detection combined with machine vision is used to monitor the status of minute structures.

[0025] The following is the data collection scheme for equipment status data in low-resolution equipment areas: It uses temperature, humidity and current sensors to acquire data over long distances with low power via LoRaWAN / LPWAN, and processes the data with a low-power microcontroller, acquiring data at high frequency only during abnormal situations.

[0026] The water area surrounding the water treatment equipment was divided into sub-regions, and water condition data were collected as follows: Based on the ArcGIS GIS module, combined with the FVCOM water flow simulation model, spatial analysis is performed on the water area around the water treatment equipment to generate a detailed water area geographic information map, clarifying the geographic boundaries of the entire water area around the water treatment equipment. Then, in the GIS module, the entire detected water area is physically divided into multiple water area sub-regions, either uniformly or non-uniformly. Because hydrodynamic turbulence intensity affects the pollutant diffusion rate, leading to faster water renewal in high-turbulence areas and easier sediment formation in low-turbulence areas, Lagrangian particle tracking (LPT) technology was used to analyze the flow field of each water sub-region. Multiple measurement points were deployed in each sub-region using a three-dimensional Doppler ultrasonic current meter (ADV) to measure the water flow velocity fluctuations and calculate the turbulence intensity, thus obtaining hydrodynamic turbulence intensity data. Simultaneously, considering that the distribution of microbial communities affects biofilm formation and the pollution level of the water surrounding the treatment equipment, water sampling points were set up in each sub-region. High-throughput sequencing technology was used to detect the microbial community structure in each sub-region, and fluorescence in situ hybridization (FISH) was used to label specific bacterial groups and analyze dominant species. Finally, QIIME2 bioinformatics analysis was used to calculate the microbial diversity index in each sub-region.

[0027] Furthermore, the hydrodynamic turbulence intensity and microbial diversity index of each water sub-region are quantified. The weighted average of the quantified values ​​of hydrodynamic turbulence intensity and microbial diversity index determines the water score Sy of each water sub-region. Then, a water score threshold Ysy is set, and the water score Sy of each water sub-region is compared with the water score threshold Ysy. When the water score Sy of a water sub-region is greater than or equal to the water score threshold Ysy, it indicates that the water sub-region is a low-pollution water area; when the water score Sy of a water sub-region is less than the water score threshold Ysy, it indicates that the water sub-region is a high-pollution water area. The data collection plan for highly polluted water bodies is as follows: High-precision water quality sensors are deployed using drones and underwater robots (AUVs), and water pollution components are monitored using fluorescence dissolved oxygen sensors, conductivity sensors, and pH sensors. LiDAR and ultrasonic depth sounders are used to detect the concentration of suspended solids and the thickness of deposited pollutants in the water, and a miniature spectrometer is used to monitor the content of organic pollutants and heavy metals in real time.

[0028] The data collection plan for low-pollution water body conditions is as follows: Using unmanned surface vessel (USV) and regular water sampling, samples are collected weekly or monthly and sent to the laboratory for analysis. Basic water quality parameters are monitored using an electrochemical pH sensor, a conductivity sensor, and a low-cost optical turbidimeter, and water transparency is monitored, reducing the cost of complex testing.

[0029] It should be noted that the water area score threshold Ysy is obtained by referring to the above method for obtaining the equipment score threshold Ys, and will not be repeated here.

[0030] In the waters surrounding the water treatment equipment, due to the complexity of the hydrodynamic environment, absolute isolation between different sub-regions is impossible, resulting in overlapping areas. Therefore, the overlapping areas between highly polluted and low-pollution waters are first identified using a GIS module and designated as neutralized waters. Further, dissolved oxygen concentration data in the neutralized waters are measured and calculated using fluorescence or electrochemical sensors. A dissolved oxygen threshold Yr is set. When the dissolved oxygen concentration in the neutralized waters is greater than or equal to the threshold Yr, it indicates a low level of pollution, and a low-pollution water condition data acquisition scheme should be adopted. Conversely, when the dissolved oxygen concentration is less than the threshold Yr, it indicates a high level of pollution, and a high-pollution water condition data acquisition scheme should be adopted. Furthermore, the Pandas library is used to clean the equipment status data collected from the water treatment equipment sub-region and the water condition data collected from the water area sub-region, and the Precise Time Protocol (PTP) is used to synchronize the time of each sensor node to ensure the consistency of the collected equipment status data and water condition data.

[0031] Step 2: Screen for areas that can be integrated and determine the health index of the current water treatment equipment; First, a multi-parameter dynamic time warping algorithm is used to calculate the DTW distance of the fluid shear force distribution data and corrosion potential distribution data of the water treatment equipment surface and the water treatment equipment material in the water area sub-region, as well as the quantified values ​​of hydrodynamic turbulence intensity and microbial diversity index in the water area sub-region, and then weighted summation is performed: Specifically, according to the formula: D=Q3×Jq+Q4×Fs+Q5×Sd+Q6×Ws+Ql×lj, where Q3 represents the weight of the quantified value of the fluid shear force distribution data on the water treatment equipment surface at this time, Jq represents the quantified value of the fluid shear force distribution data on the water treatment equipment surface, Q4 represents the weight of the quantified value of the corrosion potential distribution data of the water treatment equipment material at this time, Fd represents the quantified value of the corrosion potential distribution data of the water treatment equipment material, Q5 represents the weight of the quantified value of the hydrodynamic turbulence intensity at this time, Sd represents the quantified value of the hydrodynamic turbulence intensity, Q6 represents the weight of the quantified value of the microbial diversity index at this time, Ws represents the quantified value of the microbial diversity index, lj represents the path penalty term, constraining the temporal alignment path slope ≤2 to prevent excessive distortion, Ql represents the weight of the path penalty term, and D represents the final weighted distance value; Based on historical data, K-means clustering is used, and 75% of the minimum distance is set as the fusion threshold Yz. When D is less than or equal to the fusion threshold Yz, the sub-region is considered to be fusionable. When D is greater than the fusion threshold Yz, the sub-region is considered to be non-fusionable. Furthermore, for the water treatment equipment sub-region within the fusionable region, Kalman filtering is used to fuse multi-source data, generating a unified water treatment equipment status time series: Predict the device's state in the next moment:

[0032] Update the state based on the new observations:

[0033] Where Kk is the Kalman gain, Zk is the observation data, A and H are the state transition matrix and observation matrix, and Xk represents the equipment data for the entire water treatment equipment area.

[0034] For the water sub-regions within the mergeable region, a graph neural network (GNN) is used to analyze the spatial correlation of water quality and water condition data: Establish a topological graph G=(V,E) for the sub-region of the water area, where node V represents the water area monitoring point and edge E represents the water flow relationship; GCN was used for feature extraction, and data from different water sub-regions were fused to determine the water data HL for the entire water sub-region.

[0035] Furthermore, the Pearson correlation coefficient and Spearman rank correlation coefficient of equipment data and water area data are calculated to screen strongly correlated equipment data Bs and water area data Ys; the formula for calculating the health index of water treatment equipment is defined as: Hk=Qbs×Bs+QYs×Ys, where Qbs and QYs represent the weights of strongly correlated equipment data Bs and water area data Ys, and are dynamically updated through Bayesian inference; Step 3: Adjust the key parameters of the water treatment equipment in real time based on the current health index of the water treatment equipment; Based on the health index of the water treatment equipment obtained in step 2, the pump flow rate, chemical dosage, and aeration intensity parameters of the water treatment equipment are automatically adjusted through a PID control algorithm.

[0036] Specifically as follows: Step S1: Establish a PID feedback control model: The controlled objects are defined as: water pump flow rate Qsl, chemical dosage D, and aeration intensity A; Error calculation: e(t) = target value - current value; PID control output:

[0037] Where K1p represents the proportional gain, K1i represents the integral gain, and K1d represents the derivative gain; Initial PID parameters are set based on the ZN tuning method: Set an initial value for K1p and gradually increase it until the system oscillates; Adjust K1i to eliminate steady-state error, but not too much, to avoid integral saturation; Configure K1d to reduce overshoot; Adaptive adjustment of PID parameters based on the health index HL of water treatment equipment: If HI decreases, increase K1p and K1i to improve the response speed; If HI rises, reduce K1p and K1i to stabilize the operation.

[0038] Step 4: Build a remote visual management and monitoring system for water treatment equipment with early warning capabilities; Employing LoRa, NB-IoT, or Wi-Fi communication technologies enables water treatment equipment to connect to the internet, thus building an IoT access system for water treatment equipment. Based on the web front-end frameworks Vue.js and ECharts, a visualization display of water treatment equipment status and water treatment data is built; and a hierarchical alarm is set up based on RabbitMQ / Kafka message queues. When an abnormality occurs in the equipment, an SMS alarm is automatically sent and pushed to the operation and maintenance personnel.

[0039] This invention also discloses an Internet of Things-based water treatment equipment management system to implement the methods described in the above embodiments, such as... Figure 1 As shown, it includes: a data acquisition module, a status analysis and health assessment module, a parameter intelligent control module, a GIS module, and a remote monitoring and early warning module. The signal connections between each module are as follows: The GIS module is mainly used to generate detailed geographic information maps of water bodies by combining the FVCOM water flow simulation model; The data acquisition module is mainly used to divide the area into sub-regions, deploy sensors according to risk level, and collect data in real time. The status analysis and health assessment module is mainly used to screen water areas that can be integrated, integrate multiple types of data, calculate the health index of water treatment equipment, and determine the operational risks of water treatment equipment.

[0040] The intelligent parameter control module is based on the equipment health index and automatically adjusts parameters such as water pump and chemical dosage to prevent malfunctions and optimize efficiency.

[0041] The remote monitoring and early warning module is mainly used for real-time data display via network connection, and pushes alarms in a tiered manner when anomalies occur, thereby realizing remote management.

[0042] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0043] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0044] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and inventive constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0045] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0046] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0047] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A water treatment device management method based on Internet of Things, The application is characterized in that it comprises: Step 1: divide the water treatment equipment and the water area around the water treatment equipment into multiple water treatment equipment sub-regions and water area sub-regions and collect data of each sub-region; Step 2: screen the fusible region and determine the health index of the current water treatment equipment; Step 3: adjust the key parameters of the water treatment equipment in real time based on the health index of the current water treatment equipment; Step 4: construct a remote visual management and monitor and warn the water treatment equipment. In step 1, the water treatment equipment and the water area around the water treatment equipment are uniformly or non-uniformly physically divided; 2.The water treatment equipment management method based on the Internet of Things according to claim 1, characterized in that: In step 1, the fluid shear force distribution on the surface of the water treatment equipment in each water treatment equipment sub-region and the corrosion potential distribution data of the water treatment equipment material are collected, and the weighted average of the quantized values of the fluid shear force distribution on the surface of the water treatment equipment and the corrosion potential distribution data of the water treatment equipment material determines the equipment region score Fs of each water treatment equipment sub-region. The equipment region score Fs of each water treatment equipment sub-region is compared with the equipment score threshold Ys. When the equipment region score Fs of the water treatment equipment sub-region is greater than or equal to the equipment score threshold Ys, it indicates that the water treatment equipment sub-region belongs to a high-score equipment region. When the equipment region score Fs of the water treatment equipment sub-region is less than the equipment score threshold Ys, it indicates that the water treatment equipment sub-region belongs to a low-score equipment region. In step 1, the water dynamic turbulence intensity and the microbial diversity index data in each water area sub-region are collected, and the weighted average of the quantized values of the water dynamic turbulence intensity and the microbial diversity index determines the water area score Sy of each water area sub-region. The water area score Sy of each water area sub-region is compared with the water area score threshold Ysy. When the water area score Sy of the water area sub-region is greater than or equal to the water area score threshold Ysy, it indicates that the water area sub-region is a low-pollution water area. When the water area score Sy of the water area sub-region is less than the water area score threshold Ysy, it indicates that the water area sub-region is a high-pollution water area. 3.The water treatment equipment management method based on the Internet of Things according to claim 2, characterized in that: In step 1, the overlapping part of the high-pollution water area and the low-pollution water area is determined, which is denoted as the neutral water area. The water body dissolved oxygen concentration data in the neutral water area is calculated, and the water body dissolved oxygen threshold Yr is set. When the water body dissolved oxygen concentration data of the neutral water area is greater than or equal to the water body dissolved oxygen threshold Yr, the collection scheme of the low-pollution water area should be adopted. When the water body dissolved oxygen concentration data of the neutral water area is less than the water body dissolved oxygen threshold Yr, the collection scheme of the high-pollution water area should be adopted. 4.The water treatment device management method based on the Internet of Things according to claim 3, characterized in that; In step 2, the DTW distance of the quantized values of the fluid shear force on the surface of the water treatment equipment in the water treatment equipment sub-region and the corrosion potential distribution data of the water treatment equipment material and the water dynamic turbulence intensity and the microbial diversity index in the water area sub-region is calculated, and the weighted sum is determined to determine the final weighted distance value D. When D is less than or equal to the fusible threshold Yz, it indicates that the sub-region is a fusible region. When D is greater than the fusible threshold Yz, it indicates that the sub-region is a non-fusible region.

5. The water treatment device management method based on the Internet of Things according to claim 4, characterized in that: In step 2, the multi-source data of the water treatment equipment sub-region and the water area sub-region in the fusible region are fused.

6. The water treatment device management method based on the Internet of Things according to claim 5, characterized in that: ​ 7.The water treatment device management method based on the Internet of Things according to claim 6, characterized in that: In step 2, the Pearson correlation coefficient and the Spearman rank correlation coefficient of the device data and the water area data are calculated, and the strongly correlated device data Bs and water area data Ys are screened; Calculate the water treatment equipment health index. 8.The water treatment device management method based on the Internet of Things according to claim 7, characterized in that: In step 3, based on the water treatment equipment health index obtained in step 2, the key parameters of the water treatment equipment are dynamically adjusted; In step 4, the water treatment equipment is provided with networking capability, and an Internet of Things access system of the water treatment equipment is constructed; hierarchical alarm is set. 9.The water treatment device management method based on the Internet of Things according to claim 2, characterized in that: The device score threshold Ys is obtained as follows: Calculate the mean, standard deviation, median and quartile of the surface fluid shear force distribution of the water treatment equipment and the corrosion potential distribution data of the water treatment equipment material, analyze by K-means clustering, and determine the device score threshold Ys.

10. A water treatment device management system based on the Internet of Things, characterized by It comprises a data acquisition module, a state analysis and health evaluation module, a parameter intelligent control module, a GIS module, and a remote monitoring and early warning module, and the modules are signal connected; The GIS module is mainly used to generate detailed water area geographic information map in combination with the water flow simulation model FVCOM; The data acquisition module is mainly used to divide sub-regions, deploy sensors according to the risk level, and collect data in real time; The state analysis and health evaluation module is mainly used to screen the fusible water area, fuse multiple types of data, calculate the water treatment equipment health index, and judge the operation risk of the water treatment equipment; The parameter intelligent control module is mainly based on the equipment health index to automatically adjust the parameters such as water pump and dosing amount, prevent faults and optimize efficiency; The remote monitoring and early warning module is mainly used for real-time display of data, hierarchical push alarm in abnormal situation, and remote management.

Images