A system and method for predicting potassium permanganate dosage

Abstract

The present invention discloses a system and method for predicting potassium permanganate dosage. The system uses redox potential to predict the divalent manganese ion content in water and calculate the potassium permanganate dosage. The technology is particularly suitable for manganese ion removal in water treatment. The present invention utilizes a backpropagation neural network model, which, due to its advantages in nonlinear mapping and real-time prediction, can accurately establish the relationship between redox potential and divalent manganese ion concentration. This method can optimize the water treatment process, improve prediction accuracy, reduce chemical reagent waste, lower water treatment costs, and improve water treatment effectiveness.

Description

Technical Field

[0001] The present invention relates to the technical field of wastewater treatment, in particular to a system and method for predicting the dosage of potassium permanganate, which is particularly suitable for a manganese ion removal process in water treatment. Background Art

[0002] Manganese ions are a common contaminant in water treatment. Excessive levels of divalent manganese ions can adversely affect water quality and even pose a risk to human health. Traditional water treatment typically involves adding potassium permanganate to oxidize and remove divalent manganese ions from the water. However, accurately calculating the required dosage remains a pressing issue.

[0003] Currently, the concentration of divalent manganese ions in water is typically measured using chemical analysis, spectroscopy, titration, and other methods. These methods are complex, time-consuming, and unsuitable for real-time monitoring in practical applications. In water treatment, the redox potential (REDOX) is widely used as an indicator of the redox state of water. Previous studies have shown a correlation between the REDOX potential and the concentration of certain ions in water. However, existing technologies have yet to provide an effective solution for accurately converting the REDOX potential value into the concentration of divalent manganese ions and further calculating the required potassium permanganate dosage.

[0004] Therefore, a system and method for quickly, efficiently and accurately predicting the potassium permanganate dosage by using the redox potential to predict the concentration of divalent manganese ions in water and calculate the potassium permanganate dosage was developed. The system and method can improve the prediction accuracy, reduce the waste of chemical reagents, reduce water treatment costs and improve water treatment effects. Summary of the Invention

[0005] The present invention provides a system for predicting the dosage of potassium permanganate, comprising:

[0006] Redox potential sensor, used to measure the redox potential of water samples;

[0007] The data acquisition module uses mean filtering to denoise the redox potential data;

[0008] A back propagation neural network processing unit, which establishes a back propagation neural network prediction model based on the denoised redox potential data to predict the concentration of divalent manganese ions;

[0009] The dosage calculation module calculates the required potassium permanganate concentration based on the predicted divalent manganese ion concentration and the pre-set dosage ratio coefficient. The calculation formula is: ;in, C KMnO4 is the required potassium permanganate concentration, C Mn 2+is the predicted divalent manganese ion concentration, V water is the volume of the water body, k is the proportional coefficient, and the range of the proportional coefficient is 2.0 to 2.5;

[0010] Output module, showing real-time prediction of divalent manganese ion concentration and potassium permanganate dosage.

[0011] Furthermore, the output module includes a display screen for displaying the divalent manganese ion concentration and the potassium permanganate dosage, and a control interface. The output module is connected to a water treatment control system through the control interface, and is connected to a dosing device through the water treatment control system.

[0012] Furthermore, the back propagation neural network processing unit includes a training module and a prediction module. The training module is used to train the back propagation neural network model using the denoised redox potential data, and the prediction module is used to make predictions based on the trained model.

[0013] Furthermore, the backpropagation neural network model is trained using the backpropagation algorithm, and the training process is optimized using the following error function: ;in, is the real Mn 2+ concentration, is the predicted value, and N is the number of data samples.

[0014] The present invention also provides a method for predicting the dosage of potassium permanganate, which uses a system for predicting the dosage of potassium permanganate, and the method comprises:

[0015] Measure the redox potential of water samples;

[0016] The redox potential data were denoised using mean filtering;

[0017] Using the denoised redox potential data as input and the divalent manganese ion concentration in water as output, a back-propagation neural network prediction model was trained and established.

[0018] According to the established back propagation neural network prediction model, the concentration of divalent manganese ions in water is predicted;

[0019] Calculate the required amount of potassium permanganate based on the predicted divalent manganese ion concentration.

[0020] Furthermore, the amount of potassium permanganate required to be added is calculated using the following formula: ;in, C KMnO4 is the required potassium permanganate concentration, C Mn 2+ is the predicted divalent manganese ion concentration, V water is the volume of the water body,k is the proportional coefficient of the dosage, and the range of the proportional coefficient is 2.0 to 2.5.

[0021] Furthermore, the structure of the backpropagation neural network includes:

[0022] Input layer: The number of nodes is 1, and the input is the denoised redox potential data;

[0023] Hidden layer: The number of nodes is 20, which is determined by mean square error optimization;

[0024] Output layer: The number of nodes is 1, and the output is the predicted divalent manganese ion concentration.

[0025] Furthermore, the backpropagation neural network model is trained using the backpropagation algorithm, and the training process is optimized using the following error function: ;in, is the real Mn 2+ concentration, is the predicted value, and N is the number of data samples.

[0026] Furthermore, the redox potential measurement range is 880 mV to 991 mV, corresponding to a divalent manganese ion concentration in water of 0.2 mg / L to 1.5 mg / L.

[0027] Furthermore, mean filtering uses a sliding average method with a window size of 3 to remove noise from the redox potential data.

[0028] The beneficial effects of the present invention are:

[0029] The present invention utilizes a back-propagation neural network model to accurately predict the concentration of divalent manganese ions in water, thereby avoiding errors in traditional methods. Based on real-time monitoring data of the redox potential, the required dosage of potassium permanganate can be calculated in real time, thereby optimizing the water treatment process and reducing excessive dosage. By accurately predicting the concentration of divalent manganese ions, the dosage of potassium permanganate can be precisely controlled, thereby avoiding waste of chemical reagents and reducing water treatment costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0031] Figure 1 It is a line graph of predicted concentration and true value;

[0032] Figure 2 This is a flow chart of the system for predicting potassium permanganate dosage;

[0033] Figure 3 Schematic diagram of the back-propagation neural network structure;

[0034] Figure 4 Comparison chart of test set prediction results and standard curve;

[0035] Figure 5 A comparison data table of 10 sets of predicted values and true values;

[0036] Figure 6 A schematic diagram of the process steps and corresponding equipment;

[0037] Figure 7 Schematic diagram of back-propagation neural network parameters. DETAILED DESCRIPTION

[0038] The technical solution of the present invention will be described below in conjunction with the accompanying drawings of the present invention, but the described embodiments are only part of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0039] like Figure 1 Shown are the experimental data of the present invention.

[0040] The experimental design is as follows: Under ideal conditions, 27 sets of water sample data were collected: the oxidation-reduction potential (ORP) was 880-991mV, the divalent manganese ion Mn 2+ The concentration was 0.2-1.5 mg / L. The redox potential was de-noised by mean filtering and then input into the back propagation neural network for training.

[0041] Prediction and results: The trained neural network model is used to predict the redox potential data in the actual water sample and accurately predict the divalent manganese ion Mn in the water. 2+ According to the predicted results, the dosage of potassium permanganate was obtained through the calculation formula.

[0042] Effect evaluation: Compared with traditional chemical analysis methods, the error of the back propagation (BP) neural network prediction model is within 5%, with high prediction accuracy. It can realize real-time monitoring and dosage control, significantly improve the efficiency of water treatment, and reduce the waste of chemical reagents.

[0043] like Figures 1 to 7 As shown, the present invention provides a system for predicting the dosage of potassium permanganate, comprising:

[0044] Oxidation-reduction potential sensor (ORP sensor), used to measure the oxidation-reduction potential of water samples;

[0045] The data acquisition module uses mean filtering to denoise the redox potential data;

[0046] A back propagation neural network processing unit, which establishes a back propagation neural network prediction model based on the denoised redox potential data to predict the concentration of divalent manganese ions;

[0047] The dosage calculation module calculates the required potassium permanganate concentration based on the predicted divalent manganese ion concentration and the pre-set dosage ratio coefficient. The calculation formula is: ;in, C KMnO4 is the required potassium permanganate concentration, C Mn 2+ is the predicted divalent manganese ion concentration, V water is the volume of the water body, k is the proportional coefficient, and the range of the proportional coefficient is 2.0 to 2.5;

[0048] The output module displays the real-time predicted divalent manganese ion concentration and potassium permanganate dosage. The output module includes a display screen for displaying the divalent manganese ion concentration and potassium permanganate dosage, and a control interface. The output module is connected to a water treatment control system through the control interface, and is connected to a dosing device through the water treatment control system.

[0049] The back propagation neural network processing unit includes a training module and a prediction module. The training module is used to train the back propagation neural network model using the denoised redox potential data, and the prediction module is used to make predictions based on the trained model.

[0050] Specifically, the backpropagation neural network model is trained using the backpropagation algorithm, and the training process is optimized using the following error function: ;in, is the real Mn 2+ concentration, is the predicted value, and N is the number of data samples.

[0051] As a preferred embodiment, the oxidation-reduction potential sensor (ie, ORP sensor) measures the oxidation-reduction potential value in the water sample in real time as the divalent manganese ion Mn 2+ The basic data for concentration prediction. The redox potential sensor has a measurement range of 880-2000 mV and an accuracy of ±1 mV, and is suitable for divalent manganese ions Mn in water. 2+ Ideal water quality conditions are 0.2-1.5 mg / L. The ORP sensor is installed in the water treatment pipeline to ensure that a representative water sample can be collected.

[0052] As a preferred embodiment, the data acquisition module converts the analog signal from the redox potential sensor into a digital signal and performs noise reduction processing. The data acquisition module collects the redox potential data using an analog-to-digital converter (ADC) and removes noise using a mean filter with a window size of 3. The data acquisition module hardware uses an acquisition card with a sampling frequency of 1 Hz to ensure real-time performance.

[0053] As a preferred embodiment, the back propagation neural network processing unit (ie, BP neural network processing unit) predicts the redox potential data after denoising and calculates the divalent manganese ion concentration CMn in water. 2+ The present invention uses the back propagation neural network model (ie, BP neural network model) because it has strong nonlinear fitting ability and can accurately capture the redox potential of 880-991 mV and the divalent manganese ion Mn 2+ The complex relationship between concentrations of 0.2-1.5 mg / L. Through training, a stable mapping model is established.

[0054] Implementation: Use Python to build a back propagation neural network model (BP neural network model) based on the TensorFlow framework. The data input is the redox potential value, and the output is the predicted divalent manganese ion concentration CMn 2+ .

[0055] like Figure 3 and Figure 7 As shown in Figure 2, the structure of the back-propagation neural network includes:

[0056] Input layer: The number of nodes is 1, and the input is the denoised redox potential data;

[0057] Hidden layer: The number of nodes is 20, which is determined by mean square error optimization, and the Sigmoid activation function is used to enhance the nonlinear fitting ability;

[0058] Output layer: The number of nodes is 1, and the output is the predicted divalent manganese ion Mn 2+ concentration.

[0059] As a preferred embodiment, the dosage calculation module calculates the amount of potassium permanganate to be added based on the predicted divalent manganese ion concentration. The required potassium permanganate concentration is calculated by the pre-set dosage ratio coefficient. C KMnO4.

[0060] formula: ;

[0061] in, C KMnO4 is the required potassium permanganate concentration, CMn 2+ is the predicted divalent manganese ion concentration, Vwater is the volume of the water body, k The proportional coefficient is in the range of 2.0 to 2.5. After the dosage is calculated, the result is transmitted to the dosing device through the control system to adjust the amount of potassium permanganate added.

[0062] In a preferred embodiment, the output module displays real-time prediction and calculation results and feeds this data back to the water treatment control system. The output device includes a display screen and a control interface. The display screen allows operators to view predicted concentrations and dosages, while the control interface connects to an automated dosing system. The automated control system adjusts the dosing device to precisely control the potassium permanganate dosage. The control system automatically adjusts the potassium permanganate supply based on a set threshold to prevent overdosing.

[0063] like Figures 1 to 7 The present invention also provides a method for predicting the dosage of potassium permanganate, using the above-mentioned system for predicting the dosage of potassium permanganate, the method comprises:

[0064] Measure the redox potential of water samples;

[0065] The redox potential data were denoised using mean filtering;

[0066] Using the denoised redox potential data as input and the divalent manganese ion concentration in water as output, a back-propagation neural network prediction model was trained and established.

[0067] According to the established back propagation neural network prediction model, the concentration of divalent manganese ions in water is predicted;

[0068] Calculate the required amount of potassium permanganate based on the predicted divalent manganese ion concentration.

[0069] The amount of potassium permanganate required to be added is calculated using the following formula: ;in, C KMnO4 is the required potassium permanganate concentration, CMn 2+ is the predicted divalent manganese ion concentration, V water is the volume of the water body, k is the proportional coefficient of the dosage, and the range of the proportional coefficient is 2.0 to 2.5.

[0070] Before measuring water samples, water sampling is required. Under ideal conditions (ignoring interference from turbidity, temperature, and pH), an ORP sensor is installed at the inlet of the water treatment pipeline to collect ORP data for 27 sets of water samples. This data is transmitted in real time via a data acquisition module.

[0071] The data acquisition module uses mean filtering to denoise the collected redox potential data. The window size is 3, meaning the average of three consecutive data points is taken. For example, for the redox potential sequence [947, 948, 946], the denoised value is 947 mV. This method effectively smooths noise and ensures the stability of the input data.

[0072] Training and optimization of back-propagation neural network models:

[0073] Training data: Use a dataset with known redox potentials (ORPs) and corresponding divalent manganese ion concentrations. The dataset should cover the divalent manganese ion concentration range in water (0.2-1.5 mg / L) and the corresponding redox potential values.

[0074] The network structure adopts a back-propagation neural network structure with one hidden layer: the number of input layer nodes is 1 (ORP value); the number of output layer nodes is 1 (predicted divalent manganese ion concentration); the hidden layer has 20 nodes, and the Sigmoid activation function is used to enhance the nonlinear fitting ability.

[0075] Training process:

[0076] The weights are optimized using the backpropagation algorithm and gradient descent method. The learning rate is set to 0.01 to ensure convergence stability. The error function formula is: ;in, is the real Mn 2+ concentration, is the predicted value, and N is the number of data samples (27).

[0077] Stop condition: error E<0.001 or 500 iterations.

[0078] The results showed that after training, the average prediction error of the back-propagation neural network model for 27 sets of data was 2.8%.

[0079] Furthermore, to prevent overfitting, we used early stopping, which stops training when the validation set error stops decreasing. Five validation sets were randomly selected from the 27 data sets.

[0080] Furthermore, to improve the effectiveness of backpropagation neural network training, the input data can be normalized. The normalization method used in this experiment is Min-Max normalization: scaling the data to the interval [0,1].

[0081] Integration and debugging of the device: The redox potential sensor, data acquisition module, back propagation neural network processing unit and dosage calculation module are interconnected via the Modbus protocol. The data flow is:

[0082] Sensor outputs redox potential → acquisition module denoising → neural network prediction → dosage calculation → output control.

[0083] like Figure 5 As shown, in a laboratory environment, 27 groups of known Mn 2+ The system was verified by water samples with a concentration of 100 μg / cm2. The results showed that:

[0084] ORP=880 mV, predicted Mn 2+ =0.21 mg / L (actual 0.20 mg / L), error 5%;

[0085] ORP=947 mV, predicted Mn 2+ =0.50 mg / L (actual 0.50 mg / L), error 0%;

[0086] ORP=991 mV, predicted Mn 2+ = 1.48 mg / L (actual 1.50 mg / L), error 1.33% (not shown in the figure).

[0087] The average error is 2.8%, and the dosage control error is less than 5%, meeting the water treatment needs under ideal conditions.

[0088] The method provided by this invention is not only suitable for drinking water treatment but can also be widely applied to industrial wastewater treatment, environmental water treatment, and other fields. By predicting the divalent manganese ion concentration in water in real time and accurately calculating the dosage of potassium permanganate, the efficiency of the water treatment process can be significantly improved, resource utilization can be optimized, and environmental pollution can be reduced.

Claims

1. A system for predicting potassium permanganate dosage, characterized in that: include: Redox potential sensor, used to measure the redox potential of water samples; The data acquisition module uses mean filtering to denoise the redox potential data; The back propagation neural network processing unit establishes a back propagation neural network prediction model based on the denoised redox potential data to predict the divalent manganese ion concentration. The back propagation neural network processing unit includes a training module and a prediction module. The training module is used to train the back propagation neural network model using the denoised redox potential data, and the prediction module is used to make predictions based on the trained model. The back propagation neural network model is trained using a back propagation algorithm, and the training process is optimized using the following error function: ； in, is the real Mn 2+ concentration, is the predicted value, N is the number of data samples; The dosage calculation module calculates the required potassium permanganate concentration based on the predicted divalent manganese ion concentration and the pre-set dosage ratio coefficient. The calculation formula is: ； in, C KMnO4 is the required potassium permanganate concentration, C Mn 2+ is the predicted divalent manganese ion concentration, V water is the volume of the water body, k is the proportional coefficient, and the range of the proportional coefficient is 2.0 to 2.5; Output module, showing real-time prediction of divalent manganese ion concentration and potassium permanganate dosage.

2. The system for predicting potassium permanganate dosage according to claim 1, wherein The output module includes a display screen for displaying the concentration of divalent manganese ions and the dosage of potassium permanganate, and a control interface. The output module is connected to a water treatment control system through the control interface, and is connected to a dosing device through the water treatment control system.

3. A method for predicting the dosage of potassium permanganate, characterized in that: Using the system for predicting potassium permanganate dosage according to claim 1, the method comprises: Measure the redox potential of water samples; The redox potential data were denoised using mean filtering; Using the denoised redox potential data as input and the divalent manganese ion concentration in water as output, a back-propagation neural network prediction model was trained and established. According to the established back propagation neural network prediction model, the concentration of divalent manganese ions in water is predicted; Calculate the required amount of potassium permanganate based on the predicted divalent manganese ion concentration.

4. The method for predicting potassium permanganate dosage according to claim 3, wherein The structure of the back-propagation neural network includes: Input layer: The number of nodes is 1, and the input is the denoised redox potential data; Hidden layer: The number of nodes is 20, which is determined by mean square error optimization; Output layer: The number of nodes is 1, and the output is the predicted divalent manganese ion concentration.

5. The method for predicting potassium permanganate dosage according to claim 3, wherein The redox potential measurement range is 880 mV to 991 mV, corresponding to a divalent manganese ion concentration in water of 0.2 mg / L to 1.5 mg / L.

6. The method for predicting potassium permanganate dosage according to claim 3, wherein Mean filtering uses a sliding average method with a window size of 3 to remove noise from the redox potential data.

Images