Flocculation process intelligent dosing control method based on image information

Through the image information fusion model, the dosage amount during the flocculation process is adjusted in real time, which solves the problem of inaccurate dosing under manual control, improves the efficiency and reliability of water supply treatment, and reduces cost and energy consumption.

CN118915642AActive Publication Date: 2024-11-08HARBIN INSTITUTE OF TECHNOLOGY (SHENZHEN) (INSTITUTE OF SCIENCE AND TECHNOLOGY INNOVATION HARBIN INSTITUTE OF TECHNOLOGY SHENZHEN)

Patent Information

Application Number
CN202410944757.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-15
Publication Date
2024-11-08
Estimated Expiration
2044-07-15

AI Technical Summary

Technical Problem

The existing water supply treatment technology in Chinese medicine administration control relies on manual manual control, and does not use image information, resulting in inaccurate dosage, affecting the stability and treatment efficiency of water quality, and being unable to respond quickly to changes in water quality, limiting the efficiency and reliability of water supply treatment.

Method used

Using the intelligent drug administration control method based on image information, the water inlet, process and effluent water quality data, equipment working conditions and flocculation area video information are collected, and the water quality working conditions and image drug administration data set are fused into the water quality working conditions and image drug administration data set, and the K nearest neighbor regression sub-model and The target detection sub-model generates adjustable parameters, is embedded in the water feeding treatment equipment control system, and adjusts the dosage in real time.

Benefits of technology

Accurate control of dosage is achieved, the efficiency and reliability of water feeding treatment is improved, operating costs and energy consumption are reduced, and water quality is monitored and predicted in real time through big data analysis, and the flocculation process is optimized.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118915642A_ABST
    Figure CN118915642A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of sewage treatment, in particular to a flocculation process intelligent dosing control method based on image information. Acquiring an inlet water quality monitoring data set, a process water quality monitoring data set, an outlet water quality monitoring data set, an equipment working condition monitoring data set, a chemical dosage monitoring data set and a flocculation area surface state monitoring data set; the inflow water quality, the process water quality, the effluent water quality, the equipment working condition and the dosing amount monitoring data set are fused into a water quality working condition dosing fusion data set, and the flocculation area surface state and dosing amount monitoring data set are fused into an image dosing fusion data set; and inputting the water quality working condition dosing fusion data set into the parameter-adjustable K neighbor regression sub-model, and inputting the image dosing fusion data set into the parameter-adjustable target detection sub-model. And fusing two model results into a graph information fusion model, and fusing according to a weight coefficient after percentage error normalization.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment, and in particular to an intelligent dosing control method for a flocculation process based on image information. Background Art

[0002] Direct supply of raw water without treatment will cause serious health and environmental problems. Raw water may contain harmful microorganisms, heavy metals, pesticide residues and other chemical pollutants, and drinking it directly will cause diseases and long-term health hazards. At the same time, the quality of untreated raw water is unstable and easily affected by environmental changes and pollution. It will also cause pollution to the inner wall of the water supply pipe, increase maintenance costs, and damage the ecological environment. Therefore, it is necessary to go through a strict water supply treatment process to ensure that the water quality meets the standards and guarantee water safety.

[0003] Flocculant addition plays a key role in water treatment. It neutralizes the charge of suspended particles in the water, causing small particles to aggregate into larger flocs, which facilitates the subsequent sedimentation and filtration process. This not only effectively removes turbidity and organic matter in the water, but also significantly reduces the turbidity and pollutant content in the water, and improves the transparency and purity of the water quality. The addition of flocculants optimizes the entire water treatment process, improves treatment efficiency, ensures the safety and quality of water supply, and provides important protection for public health and environmental protection.

[0004] Existing water treatment dosing control relies on manual dosing without using image information, which has many disadvantages. Manual dosing of flocculants is not only inefficient, but also prone to inaccurate dosage due to human error, affecting treatment effects and water quality stability. In addition, manual operation is difficult to monitor and adjust in real time, and cannot respond quickly to changes in water quality. Image information can provide real-time visual data on water quality, help achieve automated and intelligent control, improve the accuracy and reaction speed of flocculant dosing, thereby optimizing treatment effects and reducing operating costs.

[0005] In summary, the prior art has a problem in which the dosing control process relies on manual control without paying attention to image information, resulting in an inability to ensure that the dosage can accurately meet the needs of the water treatment process. The effluent from the water treatment process does not meet the drinking water standards, limiting the efficiency and reliability of the water treatment. Summary of the invention

[0006] The purpose of the present invention is to provide an intelligent dosing control method for flocculation process based on image information, so as to solve the problem that the dosing control in the prior art only relies on manual control and ignores the guiding role of image information on the change of dosing state, resulting in the inability to ensure that the dosage can accurately meet the needs of the water treatment process, and the water effluent from the water treatment does not meet the drinking water standards, which limits the efficiency and reliability of the water treatment.

[0007] To achieve the above object, the present invention adopts the following technical solution, a method for intelligent dosing control of flocculation process based on image information, comprising the following steps:

[0008] S1. Sample the inlet water quality indicators to obtain an inlet water quality monitoring data set, sample the process water quality indicators to obtain a process water quality monitoring data set, sample the effluent water quality indicators to obtain an effluent water quality monitoring data set, collect equipment data for water supply and water treatment equipment, and obtain an equipment condition monitoring data set; monitor the dosage of the dosing device in the flocculation area of ​​the sedimentation tank to obtain a dosage monitoring data set; monitor the video file of the surface of the flocculation area of ​​the sedimentation tank to obtain a flocculation area surface state image data set;

[0009] S2, merge the inlet water quality monitoring data set, process water quality monitoring data set, effluent water quality monitoring data set, equipment condition monitoring data set and dosage monitoring data set into a water quality condition dosage fusion data set; merge the flocculation zone surface state image data set and the dosage monitoring data set into an image dosage fusion data set;

[0010] S3, input the water quality condition dosing fusion data set into the K nearest neighbor regression sub-model with adjustable parameters; input the image dosing fusion data set into the target detection sub-model with adjustable parameters;

[0011] S4, fusing the two model results into an adjustable parameter image information fusion model, fusing them according to the weight coefficient after the percentage error is normalized, and the obtained adjustable parameter fusion model is embedded in the control system terminal of the water treatment dosing equipment;

[0012] S5. Based on the obtained adjustable parameter image information fusion model, the dosing amount of the dosing equipment in the flocculation zone of the sedimentation tank in the dosing process of water supply water treatment is controlled according to the output result.

[0013] Furthermore, in the S1, the monitoring time of the inlet water quality monitoring data set, the process water quality monitoring data set and the equipment operating condition monitoring data set is time T, and the monitoring time of the outlet water quality monitoring data set is time T-1.

[0014] Furthermore, in the S1, the method for acquiring the flocculation zone surface state image dataset is: capturing the characteristics of the flocs on the surface of the flocculation zone of the sedimentation tank from multiple angles, extracting the number, morphology, relative size, and existence time of the flocs on the surface of the flocculation zone of the sedimentation tank from the aerobic tank video state monitoring dataset through a general target monitoring algorithm, and constructing the flocculation zone surface state image dataset.

[0015] Furthermore, in the S1, the data processing method is: filling missing values ​​and deleting outliers.

[0016] Furthermore, in S2, the data fusion method is: aligning the data rows and data columns of the data set, and setting the data interval to the minimum sampling time.

[0017] Furthermore, in the S3, the construction method of the K nearest neighbor regression sub-model is: first, prepare and preprocess 25% of the data set, and divide it into a training set, a validation set, and a test set; store the training data, and when new data needs to be predicted, the algorithm calculates the distance between the new data point and all the stored training data points; then, select the K nearest neighbors, and perform regression fitting based on the target values ​​of these neighbors; repeat the above process until the loss function percentage error converges to less than 10% or reaches a predetermined number of training rounds of 1000, and outputs the adjustable parameters at the same time.

[0018] Furthermore, in the S3, the method for constructing the target detection sub-model is as follows: first, prepare and preprocess 25% of the data set, and divide it into a training set, a validation set, and a test set; then initialize the network weights, select the loss function, and the optimizer; during the training process, calculate the output and loss value through forward propagation, and then update the weights through back propagation; use multiple batches of data for training in multiple training cycles, and use the validation set to evaluate the model performance after each cycle and adjust the hyperparameters; repeat the above process until the loss function percentage error converges to less than 10% or reaches a predetermined number of training rounds of 1,000, and output the adjustable parameters at the same time.

[0019] Furthermore, the step S5 includes the following steps:

[0020] S51, setting the parameters of the image information fusion model as temporary adjustable parameters, inputting 100% of the fusion data into the image information fusion model, and the model outputting the recommended dosage of the dosing device;

[0021] S52, the control module controls the water treatment dosing equipment in the flocculation zone of the sedimentation tank during the water treatment dosing process according to the dosing amount recommended by the model;

[0022] S53, monitoring the water quality of the water samples collected through the real-time effluent sampling tube according to the data acquisition device, obtaining the effluent water quality, and obtaining a effluent water quality monitoring data set at time T;

[0023] S54, judging whether the water quality index meets the standard, if the water quality index meets the standard, obtaining the water supply and discharge instruction to allow the water supply.

[0024] Beneficial effects of the present invention:

[0025] 1. It solves the problem that the dosing control in the prior art only relies on manual control and ignores the guiding role of image information on the change of dosing state. The dosing amount can accurately meet the needs of the water treatment process, thereby improving the efficiency and reliability of water treatment;

[0026] 2. The fusion model can use image information to accurately adjust the dosage of flocculation reagents according to real-time and historical data, monitor and predict water quality in real time through big data analysis, improve the accuracy and efficiency of water treatment, and reduce operating costs and energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic flow diagram of the method of the present invention;

[0028] Figure 2 Schematic diagram of monitoring sites of the method of the present invention;

[0029] Figure 3 It is a control module structure diagram of the method of the present invention. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0031] Example 1

[0032] An intelligent dosing control method for a flocculation process based on image information comprises the following steps:

[0033] S100, monitor water quality, equipment operating conditions, dosage, and flocculation zone video information using data acquisition devices

[0034] SA100, water quality index monitoring and equipment condition detection based on data acquisition device

[0035] SA1001. Monitor the water quality of the water samples collected through the inlet sampling pipe according to the data acquisition device to obtain an inlet water quality monitoring data set;

[0036] SA10011. Obtain the historical influent sampling data set of the target water treatment plant;

[0037] SA10012. Perform data preprocessing, fill missing values, and delete outliers according to the historical water sampling data set;

[0038] SA10013. Configure parameters of water quality monitoring instrument according to the fluctuation characteristics of water quality indicators.

[0039] SA1002. Monitor the water quality of water samples collected through the sampling tubes of the mixing area of ​​the sedimentation tank, the flocculation area of ​​the sedimentation tank, the sedimentation area of ​​the sedimentation tank, the filter tank, the disinfection tank, the deep treatment, and the post-treatment according to the data acquisition device to obtain the process water quality monitoring data set;

[0040] SA10021. Obtain the historical process sedimentation tank mixing area, sedimentation tank flocculation area, sedimentation tank sedimentation area, filter tank, disinfection tank, deep treatment, and post-treatment sampling data sets of the target water treatment plant;

[0041] SA10022. Sampling data sets according to past process segments, preprocessing data, filling missing values, and removing outliers;

[0042] SA10023. Configure parameters of water quality monitoring instrument according to the fluctuation characteristics of water quality indicators.

[0043] SA1003. Monitor the water quality of the water samples collected through the outlet sampling pipe according to the data acquisition device to obtain an outlet water quality monitoring data set; wherein the water quality data acquisition device includes at least three water quality monitors at each location to obtain an average value to reduce errors;

[0044] SA10031. Obtain the historical effluent sampling data set of the target water treatment plant;

[0045] SA10032. Perform data preprocessing, fill missing values, and delete outliers according to the past water discharge section sampling data set;

[0046] SA10033. Configure parameters of water quality monitoring instrument according to the fluctuation characteristics of water quality indicators.

[0047] SA1004. Obtain equipment condition monitoring data sets by collecting equipment data for water treatment equipment; wherein the monitoring time of the inlet water quality monitoring data set, the process water quality monitoring data set and the equipment condition monitoring data set is time T, and the monitoring time of the outlet water quality monitoring data set is time T-1;

[0048] SA10041. Obtain the equipment operating condition data set of the target water treatment plant;

[0049] SA10042. Perform data preprocessing on the equipment operating condition data set, fill in missing values, and delete outliers.

[0050] Specifically, in the present embodiments SA1001, SA1002, and SA1003, the target water treatment plant inlet water quality indicators include turbidity, chromaticity, temperature, pH value, conductivity, total dissolved solids, total hardness, chemical oxygen demand, biochemical oxygen demand, chloride, sulfate, nitrate, metal ions (such as iron, manganese, copper, lead, etc.), total coliform group and total bacteria count at the time of inlet water; the target water treatment plant process water quality indicators include turbidity, pH value, chloride of the sedimentation tank mixing zone, sedimentation tank flocculation zone, sedimentation tank sedimentation zone, filter tank, disinfection tank, deep treatment, and post-treatment; the target water treatment plant effluent water quality indicators include turbidity, chromaticity, pH value, residual chlorine, total dissolved solids, total hardness, fluoride, chloride, nitrate, metal ions, total coliform group, total bacteria count and disinfection by-products at the time of effluent water.

[0051] The target sewage treatment plant is a professional sewage treatment organization that adopts biochemical treatment to treat sewage. The sewage undergoes inlet regulation, outlet regulation, mixing process, flocculation process, sedimentation process, filtration process, disinfection reaction, deep treatment and post-treatment and other sewage biochemical or physicochemical treatment processes in the sewage treatment equipment of the target sewage treatment plant.

[0052] Specifically, in this embodiment SA1004, the raw water undergoes sewage biochemical or physicochemical treatment processes such as inlet regulation, outlet regulation, mixing process, flocculation process, sedimentation process, filtration process, disinfection reaction, deep treatment and post-treatment in the water treatment equipment of the target sewage treatment plant. The dosing time, mixing reaction time, flocculation time, sedimentation time, filtration time and disinfection contact time are adjusted based on the control system to achieve reasonable arrangement of mixing conditions, flocculation conditions, sedimentation conditions, filtration conditions and disinfection conditions of the water treatment equipment and normal progress of deep treatment, so that the water supply can effectively undergo treatment processes such as inlet regulation, outlet regulation, mixing process, flocculation process, sedimentation process, filtration process, disinfection reaction, deep treatment and post-treatment.

[0053] Data collection is performed on the control system used to control the water treatment equipment for water treatment, and data collection is performed on the actual operation data of the water treatment equipment to obtain the equipment status monitoring data set. The data types in the equipment condition monitoring data set include dosing time, mixing reaction time, flocculation time, sedimentation time, filtration time and disinfection contact time: Data collection is performed on the dosing control system used to control the water treatment equipment for water treatment,

[0054] SB100, monitor the dosage of the flocculation area of ​​the sedimentation tank according to the data acquisition device

[0055] Data collection is performed on dosage data of water treatment equipment to obtain a dosage monitoring data set, in which the data types of the dosage monitoring data set include the dosage of the reagent of the water treatment equipment in the flocculation zone of the sedimentation tank.

[0056] SC100, based on the data acquisition device, monitors the surface image information of the flocculation area of ​​the sedimentation tank

[0057] At least three high-resolution cameras are used to capture the characteristics of floccules on the surface of the flocculation zone of the sedimentation tank from multiple angles. The number, morphology, relative size, and existence time of floccules on the surface of the flocculation zone of the sedimentation tank are extracted from the aerobic tank video state monitoring data set through a general target monitoring algorithm to construct a flocculation zone surface state image data set.

[0058] According to the surface conditions of the flocculation area of ​​the sedimentation tank of the water treatment plant, the resolution and coverage of the required image are determined. At the same time, check the possible influencing factors around to ensure that the selected camera has waterproof, dustproof, anti-corrosion and other functions to adapt to the complex environmental conditions of the sewage treatment plant. The camera is installed at the edge of the aerobic pool and the high platform to ensure that the surface of the aerobic pool can be fully covered to avoid monitoring blind spots. The camera is located 20 cm below the edge of the aerobic pool. At the same time, adjust the angle of the camera to obtain the best monitoring effect to avoid factors such as sunlight reflection affecting the image quality. The camera angle is 35 degrees to the gravity line. Mounting brackets and fixing equipment are installed at the camera layout position. The bracket has anti-corrosion performance and can be used for a long time in the environment of the sewage treatment plant. The fixing equipment should be firm to prevent the camera from being offset due to external forces. Use waterproof network cables to arrange the power cord of the camera to ensure stable power supply. It can be equipped with power protection equipment to prevent power interruptions or fluctuations. Install a protective cover on the edge of the camera to prevent the camera from being affected by external environments such as rain, dust, and chemical corrosion.

[0059] The camera system was debugged and optimized through preliminary experiments. The camera angle and focal length were debugged to ensure that the monitoring picture was clear and the coverage was comprehensive. Secondly, the camera was connected to the monitoring system to test image transmission and storage to ensure that the system was running normally. The stability and reliability of the system were checked through functions such as real-time monitoring and historical record playback. Finally, a regular maintenance cycle was set up, which was set to 24h. The camera lens was cleaned regularly, the working status of the equipment was checked, and possible problems were dealt with in a timely manner to ensure the long-term stable operation of the monitoring system.

[0060] The schematic diagram of the monitoring site at the water supply plant is as follows Figure 2 shown.

[0061] S200, fusion of multi-source monitoring data sets into water quality condition dosing fusion data set and image dosing fusion data set

[0062] The data fusion method aligns the data rows and columns of the data set, and the data interval is set to the minimum sampling time.

[0063] SA200, merge the inlet water quality monitoring data set, process water quality monitoring data set, outlet water quality monitoring data set, equipment condition monitoring data set and dosage monitoring data set into a water quality condition dosage fusion data set;

[0064] SB200, fusion of the flocculation zone surface state image dataset and the dosage monitoring dataset into an image dosage fusion dataset;

[0065] S300, build adaptive model, perform model training and loss optimization

[0066] These include the SA300 K-nearest neighbor regression sub-model and the SB300 target detection sub-model.

[0067] SA3001. Build the adjustable parameter K nearest neighbor regression sub-model, wherein the adjustable parameter adaptive model parameters include the number of nearest neighbors and the distance metric power;

[0068] SA3002: Use 25% of the water quality condition and dosing fusion data set as input variables to train the K nearest neighbor regression sub-model and obtain temporary adjustable parameters, including inputting the water quality condition and dosing fusion data set into the constructed K nearest neighbor regression sub-model.

[0069] The K nearest neighbor regression submodel calculates the distance between the sample to be predicted and all training samples, selects the K nearest neighbors, and then makes predictions based on the target values ​​of these neighbors. For the point to be predicted, the K nearest neighbor regression submodel calculates the distance between it and each training sample, selects the K nearest sample points as neighbors. Then, the target values ​​of these neighbors are averaged to obtain the final prediction value.

[0070] The construction method of the K nearest neighbor regression sub-model includes the following steps: First, prepare and preprocess 25% of the data set and divide it into a training set, a validation set and a test set. The training data is stored, and when new data needs to be predicted, the algorithm calculates the distance between the new data point and all stored training data points. Then, the nearest K neighbors are selected and regression fitting is performed based on the target values ​​of these neighbors. The above process is repeated until the loss function percentage error converges to less than 10% or reaches a predetermined number of training rounds of 1000, and the adjustable parameters are output at the same time.

[0071] The mathematical model of the constructed K nearest neighbor regression sub-model is:

[0072]

[0073]

[0074] x * is the new input feature vector;

[0075] x i is the feature vector of the i-th training sample;

[0076] x *,j is x * The jth feature of

[0077] x i,j is x i The jth feature of

[0078] p is the distance metric power

[0079] is the predicted output value for the new input;

[0080] k is the number of nearest neighbors, which is also d(x *, x i )The smallest k values, corresponding to the index {i1, i2, i3, ~, i k}.

[0081] SB3001. Build an adjustable parameter target detection sub-model, where the adjustable parameter adaptive model consists of (1) convolutional layer; (2) activation function; (3) pooling layer; (4) fully connected layer.

[0082] SB3002, 25% of the image drug fusion dataset is used as input variables to train the K nearest neighbor regression sub-model and obtain temporary adjustable parameters. The main structure of the target detection sub-model includes 13 convolutional layers, 5 pooling layers, 3 fully connected layers and activation functions. Each convolutional layer extracts the features of the input image by applying a convolution kernel, and applies an activation function after each convolution operation to introduce nonlinearity and enhance the expressiveness of the model. The number of convolution kernels increases layer by layer to capture more complex features. Each pooling layer is used to reduce the size of the feature map, reduce computational complexity and prevent overfitting. The final fully connected layer combines and classifies the extracted features and outputs the predicted label of the image. The target detection sub-model achieves efficient image feature extraction and classification through this hierarchical structure and activation function. The target detection sub-model layer structure is distributed as follows: first, there are 2 convolutional layers, each of which is followed by an activation function, followed by a maximum pooling layer. Next are 3 convolutional layers, each of which is followed by an activation function, followed by a maximum pooling layer. Then there are 3 convolutional layers, each followed by an activation function, followed by a max pooling layer. Next are 3 convolutional layers, each followed by an activation function, followed by a max pooling layer. Finally, there are 3 convolutional layers, each followed by an activation function, followed by a max pooling layer. After the convolutional and pooling layers, there are 3 fully connected layers, each followed by an activation function, and the last fully connected layer followed by an activation function.

[0083] The construction method of the target detection sub-model includes the following steps: First, prepare and preprocess 25% of the data set and divide it into training set, validation set and test set. Then initialize the network weights, select the loss function and optimizer. During the training process, the output and loss value are calculated by forward propagation, and the weights are updated by back propagation. In multiple training cycles, multiple batches of data are used for training, and the model performance is evaluated with the validation set after each cycle to adjust the hyperparameters. Repeat the above process until the loss function percentage error converges to less than 10% or reaches the predetermined number of training rounds of 1000 rounds, and the adjustable parameters are output at the same time.

[0084] The mathematical model of the target detection sub-model built is:

[0085] (1) Convolutional layer The formula for convolution operation is as follows:

[0086]

[0087] in:

[0088] x, input feature map, each element represents the pixel value at a specific position;

[0089] y, output feature map, each element represents the pixel value after convolution;

[0090] w, convolution kernel weight, represents the weight of the filter;

[0091] b. Bias, a constant added to the convolution result;

[0092] i, j, position index in the feature map;

[0093] k, channel index of the output feature map;

[0094] m, n, position index in the convolution kernel;

[0095] c. Channel index of the input feature map.

[0096] (2) The activation function formula is as follows:

[0097] f(x) = max(0, x)

[0098] in:

[0099] x, the output value of the convolutional layer.

[0100] (3) The pooling layer formula is as follows:

[0101] y i,j,k =max(x i+m,j+n,k ), where (m, n)∈P

[0102] in:

[0103] x, input feature map;

[0104] y, output feature map;

[0105] P, the size of the pooling window (e.g., 2x2).

[0106] (4) The formula of the fully connected layer is as follows:

[0107]

[0108] in:

[0109] x, input feature vector;

[0110] y, output vector;

[0111] w, weight matrix;

[0112] b. Bias;

[0113] i, j, vector index.

[0114] S400, the K nearest neighbor regression sub-model and the target detection sub-model are fused into a graph information fusion model, and the weight coefficients after the percentage error normalization are fused, and the adjustable parameter adaptive model is embedded in the control system terminal of the water treatment dosing equipment

[0115] The module of intelligent dosing control system for flocculation process based on graph information is as follows: Figure 3 shown.

[0116] The mathematical model of the image information fusion model is:

[0117] 1. Calculate RMSE separately

[0118]

[0119]

[0120] 2. Calculate weights

[0121]

[0122]

[0123] 3. Calculate normalized weights

[0124]

[0125]

[0126] 4. Calculate the weighted fusion value

[0127] y i =w1yi1 +w2y i2

[0128] in:

[0129] x i1 is the input value of the K nearest neighbor regression sub-model;

[0130] y i1 is the output value of the K nearest neighbor regression sub-model;

[0131] x i1 is the input value of the target detection sub-model;

[0132] y i1 is the output value of the target detection sub-model;

[0133] p i is the true value corresponding to the input value;

[0134] RMSEANN(p i ,y i1 ) is the root mean square error of the K nearest neighbor regression submodel;

[0135] RMSETD(p i ,y i2 ) is the root mean square error of the target detection sub-model;

[0136] is the weight of the K nearest neighbor regression sub-model;

[0137] is the weight of the target detection sub-model;

[0138] w1 is the normalized weight of the K nearest neighbor regression submodel;

[0139] w2 is the normalized weight of the target detection sub-model;

[0140] y i Weighted fusion value.

[0141] S500, input the fusion data into the image information fusion model, and control the water treatment dosing equipment in the flocculation zone of the sedimentation tank in the water treatment dosing process according to the image information fusion model and the adaptive parameters.

[0142] S510, setting the parameters of the image information fusion model as temporary adjustable parameters, inputting 100% of the fusion data into the image information fusion model, and the model outputting the recommended dosage of the dosing device;

[0143] S520, the control module controls the water treatment dosing equipment in the flocculation zone of the sedimentation tank during the water treatment dosing process according to the dosing amount recommended by the model;

[0144] S530, monitoring the water quality of the water samples collected through the real-time effluent sampling tube according to the data acquisition device, obtaining the effluent water quality, and obtaining a effluent water quality monitoring data set at time T;

[0145] S540, determining whether the water quality index meets the water quality index of the national standard for water supply; if the water quality index meets the water quality index of the national standard, obtaining a water supply discharge instruction to allow water supply.

[0146] Table 1 Comparison of operation data of manual dosing and model controlled dosing

[0147]

[0148]

[0149] It can be seen that the use of model control, compared with manual dosing, can significantly reduce the dosage while ensuring the water output indicators, thereby reducing operating costs and energy consumption.

[0150] The present invention is not limited to the above-mentioned optimal implementation mode. Anyone can derive other various forms of products under the inspiration of the present invention. However, no matter what changes are made in the shape or structure, all technical solutions that are the same or similar to those of the present application fall within the protection scope of the present invention.

Claims

1. An intelligent dosing control method for flocculation process based on image information, characterized in that: The following steps are involved: S1. Sample the inlet water quality indicators to obtain an inlet water quality monitoring data set, sample the process water quality indicators to obtain a process water quality monitoring data set, sample the effluent water quality indicators to obtain an effluent water quality monitoring data set, collect equipment data for water supply and water treatment equipment, and obtain an equipment condition monitoring data set; monitor the dosage of the dosing device in the flocculation area of ​​the sedimentation tank to obtain a dosage monitoring data set; Perform video monitoring on the video files of the surface of the flocculation area of ​​the sedimentation tank to obtain an image dataset of the surface state of the flocculation area; S2, merging the inlet water quality monitoring data set, the process water quality monitoring data set, the outlet water quality monitoring data set, the equipment operating condition monitoring data set and the dosage monitoring data set into a water quality operating condition dosage fusion data set; The flocculation zone surface state image dataset and the dosage monitoring dataset are fused into an image dosage fusion dataset; S3, inputting the water quality condition dosing fusion data set into the K nearest neighbor regression sub-model with adjustable parameters; Input the image drug delivery fusion dataset into the target detection sub-model with adjustable parameters; S4, fusing the two model results into an adjustable parameter image information fusion model, fusing them according to the weight coefficient after the percentage error is normalized, and the obtained adjustable parameter fusion model is embedded in the control system terminal of the water treatment dosing equipment; S5. Based on the obtained adjustable parameter image information fusion model, the dosing amount of the dosing equipment in the flocculation zone of the sedimentation tank in the dosing process of water supply water treatment is controlled according to the output result.

2. According to claim 1, an intelligent dosing control method for flocculation process based on image information is characterized in that: In the above S1, the monitoring time of the inlet water quality monitoring data set, the process water quality monitoring data set and the equipment operating condition monitoring data set is time T, and the monitoring time of the outlet water quality monitoring data set is time T-1.

3. According to claim 1, a method for intelligent dosing control of flocculation process based on image information, characterized in that: In the above S1, the method for acquiring the flocculation zone surface state image dataset is as follows: the characteristics of the floccules on the surface of the flocculation zone of the sedimentation tank are captured from multiple angles, and the number, morphology, relative size, and existence time of the floccules on the surface of the flocculation zone of the sedimentation tank are extracted from the aerobic tank video state monitoring dataset through a general target monitoring algorithm to construct the flocculation zone surface state image dataset.

4. According to claim 1, a method for intelligent dosing control of flocculation process based on image information, characterized in that: In the above-mentioned S1, the data processing method is: filling missing values ​​and deleting outliers.

5. According to claim 1, a method for intelligent dosing control of flocculation process based on image information, characterized in that: In the above-mentioned S2, the data fusion method is: aligning the data rows and data columns of the data set, and setting the data interval to the minimum sampling time.

6. According to claim 1, a method for intelligent dosing control of flocculation process based on image information, characterized in that: In the above S3, the construction method of the K nearest neighbor regression sub-model is as follows: first, prepare and preprocess 25% of the data set and divide it into a training set, a validation set and a test set; store the training data, and when new data needs to be predicted, the algorithm calculates the distance between the new data point and all the stored training data points; then, select the K nearest neighbors and perform regression fitting based on the target values ​​of these neighbors; repeat the above process until the loss function percentage error converges to less than 10% or reaches a predetermined number of training rounds of 1000, and outputs the adjustable parameters at the same time.

7. According to claim 1, a method for intelligent dosing control of flocculation process based on image information, characterized in that: In the above S3, the method for constructing the target detection sub-model is as follows: first, prepare and preprocess 25% of the data set and divide it into a training set, a validation set and a test set; then initialize the network weights, select the loss function and the optimizer; During the training process, the output and loss values ​​are calculated through forward propagation, and the weights are updated through back propagation. In multiple training cycles, multiple batches of data are used for training, and after each cycle, the validation set is used to evaluate the model performance and adjust the hyperparameters. The above process is repeated until the loss function percentage error is less than 10% and converges or the predetermined number of training rounds, 1000, is reached, and the adjustable parameters are output at the same time.

8. According to claim 1, a method for intelligent dosing control of flocculation process based on image information, characterized in that: The S5 comprises the following steps: S51, setting the parameters of the image information fusion model as temporary adjustable parameters, inputting 100% of the fusion data into the image information fusion model, and the model outputting the recommended dosage of the dosing device; S52, the control module controls the water treatment dosing equipment in the flocculation zone of the sedimentation tank during the water treatment dosing process according to the dosing amount recommended by the model; S53, monitoring the water quality of the water samples collected through the real-time effluent sampling tube according to the data acquisition device, obtaining the effluent water quality, and obtaining a effluent water quality monitoring data set at time T; S54, judging whether the water quality index meets the standard, if the water quality index meets the standard, obtaining the water supply and discharge instruction to allow the water supply.

Citation Information

Patent Citations

  • Dosing system and method based on floc feature monitoring and process feedback

    CN114545985A

  • Multi-dimensional fusion automatic medicine feeding method, device and equipment

    CN115231668A

  • MSD cover for floor mat of electric vehicle

    KR1020200138470A

Cited By

  • Intelligent coagulant adding control method and system based on image recognition and multi-parameter modeling

    CN120535101A

  • Water plant automatic energy-saving management system and method based on dosing amount prediction model

    CN121303766A

  • Method for dynamically detecting flocculation state in sewage

    CN122079332A

  • Method for dynamically detecting flocculation state in sewage

    CN122079332B