Water treatment system and water treatment process control method

Abstract

The application relates to the technical field of water treatment, and discloses a water treatment system and a water treatment process control method. A single-chamber electrolysis system based on an aluminum cathode and an IrO2-RuO2 / Ti anode is constructed to efficiently degrade NH4+-N. The system utilizes the spontaneous pH adjustment characteristic of the aluminum cathode to spontaneously adjust the solution pH to weak alkalinity, thereby providing optimal reaction conditions for free chlorine to oxidize NH4+-N, and reduces the biological enrichment and secondary pollution risk of water bodies caused by the input of medicaments compared to the prior art. Furthermore, water treatment prediction results are obtained, the water quality prediction results are used as basic indexes for dynamic adjustment of a dynamic treatment process to determine a plurality of control parameter sets, energy consumption constraints are used as screening conditions to determine an optimal parameter combination in the plurality of control parameter sets, and the water treatment process is controlled based on the parameter combination. Compared to the prior art, the application can reduce the operation cost and environmental pollution on the premise of ensuring the water quality.

Description

Technical Field

[0001] This application relates to the field of water treatment technology, specifically to a water treatment system and a water treatment process control method. Background Technology

[0002] Ammonia nitrogen wastewater has a wide range of sources, but its main origins include industrial, agricultural, and domestic sources. Discharging large amounts of ammonia nitrogen wastewater into water bodies causes numerous problems, such as eutrophication and blackening / odorization, further increasing the difficulty and cost of water treatment. Excessive ammonia nitrogen can also poison various organisms. Currently, biological denitrification is the primary method for treating ammonia nitrogen wastewater. However, nitrifying and denitrifying bacteria in biological denitrification are extremely sensitive to their environment, often leading to instability in the operation of aerobic nitrification reactions. Furthermore, most existing ammonia nitrogen wastewater treatment processes rely on a single constraint for process control, namely, ensuring that the discharged water meets emission standards. Under these circumstances, most water treatment processes suffer from high energy consumption, poor treatment efficiency, and large carbon emissions. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention provides a water treatment system and a water treatment process control method. It constructs a single-chamber electrolysis system capable of efficiently degrading ammonia nitrogen in water, and optimizes the final treatment energy consumption while using energy consumption control as a constraint. To achieve the above objectives, the technical solution adopted in this invention is as follows:

[0004] In a first aspect, a water treatment system is provided for denitrifying wastewater, comprising: a treatment device, a control device, and a processor. The treatment device is an electrolytic cell, in which multiple sensors are installed. The multiple sensors acquire multiple different types of detection data for corresponding areas and transmit the multiple detection data to the processor. The processor determines the degree of deviation between the current operating state and the optimal state of the system based on the multiple detection data, determines control parameters based on the degree of deviation, and sends the control parameters to the control device. The degree of deviation includes deviation in effluent ammonia nitrogen concentration and / or energy consumption deviation.

[0005] In some specific implementations, the electrolytic cell is provided with an electrolytic assembly, which includes a cathode and an anode arranged in parallel, and a DC power supply connected to the cathode and the anode; the cathode is an aluminum-containing metal plate, and the anode is an IrO2-RuO2 / Ti composite plate.

[0006] In some specific implementations, the various detection data include influent free chlorine concentration, influent ammonia nitrogen concentration, influent flow rate, and real-time ammonia nitrogen concentration.

[0007] In a second aspect, a water treatment process control method is provided, the method being applied to a processor in any of the above-mentioned water treatment systems, the method comprising: determining initial current densities of the cathode and anode based on free chlorine concentration; performing electrolysis treatment for a first time period using the initial current density; and obtaining multiple real-time ammonia nitrogen concentrations at multiple time points during the water treatment operation of the first time period; obtaining a predicted effluent ammonia nitrogen concentration based on the influent ammonia nitrogen concentration, the influent flow rate, and the multiple real-time ammonia nitrogen concentrations; determining whether the deviation between the predicted effluent ammonia nitrogen concentration and the standard effluent ammonia nitrogen concentration meets a preset standard; and determining control parameters based on the determination result.

[0008] In some specific implementations, the control parameters are determined based on the judgment result, including: when the deviation does not meet the preset standard, updating the initial current density in the electrolytic cell according to the degree of the deviation, performing water treatment operation based on the second time, and determining whether the deviation between the predicted concentration of ammonia nitrogen in the effluent at the second time and the standard concentration of ammonia nitrogen in the effluent meets the preset standard based on the operation process.

[0009] In some specific implementations, when the deviation meets a preset standard, multiple concentration sets are obtained; and the target ammonia nitrogen concentration is obtained by filtering the multiple concentration sets with energy consumption as a constraint, and the real-time current density is dynamically adjusted based on the target ammonia nitrogen concentration.

[0010] In some specific implementations, obtaining multiple concentration sets includes: obtaining a historical data set, calculating the similarity between the real-time data and the historical data set, and determining the associated concentration set based on the similarity distribution; the historical data set includes multiple historical datasets, each of which includes historical influent flow rate, historical influent ammonia nitrogen concentration, and historical current density; calculating the similarity between the real-time data and the historical data set includes: calculating the similarity between the real-time ammonia nitrogen concentration, the real-time influent flow rate, and the historical influent flow rate and the historical influent ammonia nitrogen concentration of each of the historical datasets, to obtain the similarity between the real-time data and each of the historical datasets.

[0011] In some specific implementations, determining the associated concentration set based on similarity distribution includes: determining the similarity value between the real-time data and multiple historical datasets, and selecting historical datasets with similarity values ​​greater than a first preset value as the associated concentration set; when the similarity value is less than the first preset value, selecting historical datasets with similarity values ​​greater than a second preset value as the basic associated concentration set, and performing optimization processing on the basic associated concentration set to obtain the associated concentration set.

[0012] In some specific implementations, the target ammonia nitrogen concentration is obtained by filtering multiple concentration sets with energy consumption as a constraint. This includes: obtaining historical current density data corresponding to each historical dataset in multiple concentration sets, determining the corresponding historical energy consumption based on the historical current density data, filtering the historical dataset with the lowest historical energy consumption as the target historical dataset, and the effluent ammonia nitrogen concentration in the target historical dataset as the target ammonia nitrogen concentration.

[0013] In some specific implementations, the predicted concentration of ammonia nitrogen in the effluent is obtained based on the influent ammonia nitrogen concentration, the influent flow rate, and multiple real-time ammonia nitrogen concentrations. This includes: obtaining multiple features corresponding to the influent ammonia nitrogen concentration, the influent flow rate, and the multiple real-time ammonia nitrogen concentrations respectively; connecting the multiple features and updating the connected features based on the weight corresponding to each feature to obtain an attention output; and obtaining the prediction result based on the attention output.

[0014] The technical solution provided in this application constructs a single-chamber electrolysis system, in which an aluminum plate-based cathode and an IrO2-RuO2 / Ti composite plate-based anode are set for efficient degradation of ammonia nitrogen. This system utilizes the spontaneous pH-regulating characteristic of the aluminum cathode to automatically adjust the solution pH to a weakly alkaline state, providing optimal reaction conditions for the oxidation of ammonia nitrogen by free chlorine. Compared to existing technologies, this reduces the risk of bioaccumulation and secondary water pollution caused by the addition of reagents. Furthermore, by obtaining water treatment prediction results, the water quality prediction results are used as the basis for dynamic adjustment of the dynamic treatment process to determine multiple sets of control parameters. Energy consumption constraints are used as a screening condition to determine the optimal parameter combination from these sets, and the water treatment process is controlled based on this parameter combination.

[0015] Compared with existing technologies, the embodiments of this application can not only improve the treatment effect of ammonia nitrogen in water and reduce the environmental damage caused by the addition of chemicals, but also coordinate water quality optimization and operating energy consumption optimization, thereby reducing operating costs and environmental pollution while ensuring the quality of effluent. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] The methods, systems, and / or procedures shown in the accompanying drawings will be further described with reference to exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein example figures represent similar mechanisms in the various views of the drawings.

[0018] Figure 1 This is a schematic diagram of the water treatment device provided in the embodiments of this application.

[0019] Figure 2 is a schematic diagram of the water treatment experimental results provided in the embodiments of this application;

[0020] Figure 2(a) shows the change in NH4+-N concentration; Figure 2(b) shows the change in pH; and Figure 2(c) shows the amount of free chlorine generated.

[0021] Figure 3 This is a schematic diagram of the water treatment system structure in an embodiment of this application.

[0022] Figure 4 This is a schematic diagram of the water treatment process control method provided in the embodiments of this application.

[0023] Figure 5 This is a schematic diagram of the processor structure provided in an embodiment of this application.

[0024] Figure 6 This is a schematic diagram of the terminal device structure provided in the embodiments of this application. Detailed Implementation

[0025] To better understand the above technical solutions, the technical solutions of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this application and the specific features in the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. In the absence of conflict, the embodiments of this application and the technical features in the embodiments can be combined with each other.

[0026] In the detailed description below, numerous specific details are illustrated with examples to provide a comprehensive understanding of the relevant guidance. However, it will be apparent to those skilled in the art that this application can be practiced without these details. In other instances, well-known methods, procedures, systems, components, and / or circuits have been described at a relatively high level without detail to avoid unnecessarily obscuring aspects of this application.

[0027] This application uses flowcharts to illustrate the execution process performed by a system according to embodiments of this application. It should be clearly understood that the execution processes in the flowcharts may not be executed sequentially. Instead, these execution processes may be executed in reverse order or simultaneously. Additionally, at least one other execution process may be added to the flowchart. One or more execution processes may be deleted from the flowchart.

[0028] Before providing a further detailed description of the embodiments of the present invention, the nouns and terms involved in the embodiments of the present invention will be explained, and the nouns and terms involved in the embodiments of the present invention shall be interpreted as follows.

[0029] (1) In response to, used to indicate the conditions or states on which the operation is performed depends. When the conditions or states on which the operation is performed are met, one or more operations may be performed in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations are performed.

[0030] (2) Based on, used to indicate the conditions or states on which the operation is performed depends. When the conditions or states on which it depends are met, one or more operations can be performed in real time or with a set delay. Unless otherwise specified, there is no restriction on the order of execution of the multiple operations.

[0031] Ammonia nitrogen (NH4+-N) is a pollutant in water bodies and has attracted much attention. Ammonia nitrogen in wastewater mainly exists in two forms: ionic ammonium and molecular ammonia. The balance between these two forms depends on the pH value, temperature and other factors of the wastewater. When the pH of the wastewater is acidic and neutral, ammonia nitrogen tends to exist in the ionic form; while under alkaline conditions, ammonia nitrogen tends to exist in the molecular form. The sum of the two parts is called total ammonia nitrogen. The hazards caused by ammonia nitrogen are: (1) Ammonia nitrogen can be converted into nitrite under certain conditions. If humans drink water with excessive ammonia nitrogen for a long time, the nitrite in the water will combine with the proteins in the human body to form nitrosamines, which will harm human health. (2) Ammonia nitrogen in water bodies will cause eutrophication, consume oxygen in the water and threaten the survival of aquatic organisms.

[0032] In existing technologies, air stripping is the primary method for treating ammonia nitrogen in water. This method involves contacting wastewater with gas, transferring ammonia nitrogen from the liquid phase to the gas phase. During this process, the pH of the wastewater needs to be adjusted to alkalinity to ensure the conversion of NH4+ to NH3. Air is then introduced into the water to expel the gaseous ammonia molecules. Air stripping is highly efficient at removing ammonia nitrogen, and the stripped water is used to produce ammonia water or ammonium sulfate, among other byproducts. However, stripping efficiency is affected by many factors, such as temperature, pH, stripping time, and the gas-liquid volume ratio. pH is the primary influencing factor, affecting the form of NH4+ in the wastewater; the higher the pH, the greater the proportion of NH3. However, subsequent treatment requires the addition of large amounts of acid to neutralize the excessively high pH. This process not only significantly increases treatment costs but also leads to reduced subsequent treatment efficiency and increased process complexity, creating a double negative impact. Furthermore, the severe air pollution caused by the emission of HN3 generated during air stripping is also a major problem with this method.

[0033] Therefore, in light of this technical background, and in order to achieve the removal of ammonia nitrogen from wastewater, this application provides a water treatment system for denitrifying wastewater. The technical approach of this water treatment system employs an electrochemical denitrification system; see [link to relevant documentation]. Figure 1 The processing device 10 in this embodiment is an electrolytic cell. An electrolytic assembly 20 is provided in the electrolytic cell, wherein the electrolytic assembly includes a cathode 21 and an anode 22 arranged in parallel, and a DC power supply 23 connected to the cathode and the anode.

[0034] Specifically, in this embodiment, the cathode is an aluminum-containing metal plate, preferably an aluminum plate; the anode is an IrO2-RuO2 / Ti composite plate. IrO2-RuO2 / Ti is a titanium-based metal oxide coated electrode material, made by loading a mixed oxide coating of IrO2 and RuO2 onto the surface of a titanium substrate. In this embodiment, it is obtained commercially. IrO2-RuO2 / Ti is an ideal anode material for chlorine evolution reactions and is widely used to treat NH4+-N in various wastewaters. Furthermore, it exhibits stable electrochemical performance and low overpotential in high chloride ion solutions. Unlike existing technologies, this embodiment uses an aluminum plate as the cathode. When aluminum is used as the cathode, the hydrogen evolution reaction produces a large amount of OH-, leading to chemical corrosion of the aluminum cathode. The resulting flocculants, such as aluminum hydroxide and Al(OH)4-, can release or consume OH- in the water, thus maintaining a stable solution pH. This provides suitable pH conditions for the oxidation of NH4+-N by free chlorine, exhibiting strong buffering capacity and maintaining the solution pH to a slightly alkaline range, which is beneficial for the oxidation of NH4+-N by free chlorine. Throughout the reaction, the concentrations of intermediate products such as nitrates and nitrites are low, achieving the conversion of NH4+-N to nitrogen.

[0035] In this embodiment, to illustrate the technical effects of using an aluminum plate as the cathode, an experimental example is provided. Specifically, three different electrolytic cells are used for electrolysis experiments, with three different electrolysis components arranged in cells of the same volume. The first group is the processing device of this embodiment, with an aluminum plate as the cathode and an IrO2-RuO2 / Ti composite plate as the anode, both with a size of 44 cm. 2 The first group has a thickness of 0.1 cm; the second group is the treatment device provided in Comparative Example 1, with the same anode as the example and the same size nickel foam cathode; the third group is the treatment device provided in Comparative Example 2, with the same anode as the example and the same size stainless steel cathode as the example cathode. The experimental wastewater in the above three groups has the same ammonia nitrogen concentration, free chlorine concentration, and chemical oxygen demand concentration, and the reaction is carried out at the same ambient temperature and reaction time.

[0036] The experimental results can be referred to Figure 2, where Figure 2(a) is a schematic diagram showing the changes in NH4+-N concentration in the Example, Control Example 1, and Control Example 2. As can be seen from Figure 2(a), for the treatment apparatus provided in Control Example 1, after the reaction lasted for 120 minutes, the NH4+-N concentration... + The -N removal rate was 20%. For the treatment apparatus provided in Control Example 2, after a reaction time of 120 min, NH4+... + The NH4+-N removal rate was 67%. For the treatment apparatus provided in the examples, the NH4+-N removal rate increased to 85% after only 90 minutes of reaction and reached 99% after 120 minutes. Regarding the pH change diagram in Figure 2(b), it can be seen that for the treatment apparatus provided in Comparative Example 1, the pH of the solution rapidly decreased from 7.0 to 3.2 within 30 minutes, and further decreased to approximately 2.8 within 120 minutes. Similarly, for the treatment apparatus provided in Comparative Example 2, the pH of the solution rapidly decreased from 7.0 to approximately 3.2 within 30 minutes, and further decreased to approximately 2.8 within 120 minutes. However, for the treatment apparatus provided in the examples, the pH of the solution decreased slowly, remaining above 5 after 60 minutes, and rising to approximately 7 after 120 minutes of electrolysis. Figure 2(c) shows a schematic diagram of free chlorine generation. It can be seen from Figure 2(c) that a large amount of active chlorine was detected in the treatment devices of Comparative Examples 1 and 2 after the same reaction time. However, combined with Figure 2(a), it can be seen that a large amount of NH4+-N was still present in the treatment devices of Comparative Examples 1 and 2 at the corresponding time. This indicates that free chlorine is difficult to oxidize NH4+-N under acidic conditions, and that it is difficult to generate more active species in the treatment devices corresponding to Comparative Examples 1 and 2. However, in the examples, when an aluminum plate was used as the cathode, all NH4+-N in the solution was removed, thus free chlorine was subsequently generated. This is because the aluminum cathode spontaneously adjusted the pH of the solution during the oxidation of NH4+-N by free chlorine, maintaining pH stability and thus promoting the reaction between NH4+-N and free chlorine. It may also be because more active species were generated. This demonstrates the advantage of using an aluminum plate as the cathode in the examples, as it can spontaneously adjust the pH of the solution, thereby promoting the oxidation of NH4+-N by free chlorine.

[0037] In this embodiment, for both the cathode and anode, current density is a key operating parameter for NH4+-N oxidation, directly determining the number of electrons participating in the NH4+-N oxidation reaction, thus affecting the NH4+-N removal efficiency. Increasing the current density increases the current and electron transfer rate on the electrodes, promoting the formation of active substances. These active substances have strong oxidizing properties, improving the NH4+-N removal efficiency. Therefore, the current density should not be too low during NH4+-N oxidation; otherwise, the NH4+-N removal rate will decrease. In this embodiment, the initial free chlorine concentration is used as a reference indicator for current density. A higher initial free chlorine concentration corresponds to a higher current density, promoting rapid formation of active substances. Conversely, a higher initial free chlorine concentration corresponds to a lower current density.

[0038] Among them, the current density is 5 mA / cm. -2 -30mAcm -2 The initial current density is set based on the desired free chlorine concentration. It is worth noting that while a higher current density improves NH4+-N removal, excessively high current densities increase energy consumption. Therefore, in this embodiment, current density control needs to consider not only the initial free chlorine concentration but also a balance between energy consumption and NH4+-N removal efficiency to improve overall water treatment control accuracy and performance.

[0039] For details, please refer to Figure 3 The water treatment system 100 according to this embodiment of the application also includes a control device (not shown), a processor 30, and multiple sensors 40. The multiple sensors are disposed in the electrolytic cell to acquire multiple different types of detection data for corresponding areas and transmit the data to the processor. The processor processes the detection data to determine the degree of deviation between the current operating state of the detection system and its optimal state, determines control parameters based on the degree of deviation, and sends the control parameters to the control device.

[0040] In this embodiment, the various detection data include influent free chlorine concentration, influent ammonia nitrogen concentration, influent flow rate, and real-time ammonia nitrogen concentration. Specifically, the free chlorine concentration is determined by a free chlorine sensor installed in the electrolytic cell. This free chlorine sensor can be an existing electrochemical sensor, which will not be elaborated further in this embodiment. The influent free chlorine concentration is obtained by collecting data from the untreated influent using the free chlorine sensor. The ammonia nitrogen concentration includes both influent ammonia nitrogen concentration and real-time ammonia nitrogen concentration, both collected by an ammonia nitrogen sensor installed in the electrolytic cell. The influent ammonia nitrogen concentration is collected from the untreated influent, while the real-time ammonia nitrogen concentration is collected at multiple time points during the treatment phase. The ammonia nitrogen sensor can be an existing digital sensor, which will not be elaborated further in this embodiment. The influent flow rate is obtained by a flow sensor installed at the influent pipe, and the influent flow rate is used to characterize the volume of the water to be treated.

[0041] In this embodiment, the degree of deviation includes water quality deviation and energy consumption deviation. Specifically, the water quality deviation is the deviation of the effluent carbon and nitrogen concentration, which is the difference between the effluent carbon and nitrogen concentration and the standard carbon and nitrogen concentration. It can be understood that the purpose of the water treatment system in this embodiment is to achieve a balance between energy consumption and NH4+-N removal efficiency, thereby improving the overall accuracy and performance of water treatment control. Therefore, the objectives of the water treatment system in this embodiment are twofold: the first objective is to control the effluent ammonia nitrogen concentration to meet the standard, and the second objective is to optimize overall energy consumption and reduce excessive energy consumption. Furthermore, since the treatment device in this embodiment uses an electrolysis component, the main energy consumption comes from the DC power supply, and the change in DC power supply energy consumption is based on current density. Therefore, controlling energy consumption in the water treatment system is equivalent to controlling the current density of the DC power supply. Thus, the control parameter in this embodiment refers to current density.

[0042] The deviation in effluent ammonia nitrogen concentration refers not to the difference between the final treated effluent ammonia nitrogen concentration and the standard ammonia nitrogen concentration, but rather to the difference between the predicted effluent ammonia nitrogen concentration and the standard ammonia nitrogen concentration. The predicted effluent ammonia nitrogen concentration characterizes the possible value of the final effluent ammonia nitrogen concentration under the current treatment conditions. If the predicted effluent ammonia nitrogen concentration is within the range defined by the standard ammonia nitrogen concentration, it indicates that the current treatment conditions can meet the final water quality requirements. When the water quality requirements are met, it is necessary to re-determine whether the energy consumption corresponding to the current treatment conditions is the optimal energy consumption solution, determine the corresponding optimal energy consumption solution and the corresponding control parameters, and control the water treatment based on these control parameters. If the predicted effluent ammonia nitrogen concentration is higher than the range defined by the standard ammonia nitrogen concentration, it indicates that the current treatment conditions cannot meet the final water quality requirements. In this case, the current control parameters need to be updated, and a second prediction needs to be performed based on the updated control parameters until the final water quality requirements are met. Similarly, for the water treatment system that meets the final water quality requirements, the optimal energy consumption solution is determined, and then the control parameters corresponding to the determined optimal energy consumption solution are used as the final control parameters.

[0043] It can be understood that the water treatment system provided in this embodiment can treat ammonia nitrogen in water by constructing an electrolysis system, and control the overall water treatment process by using a processor.

[0044] For specific water treatment process control methods, please refer to... Figure 4 The method includes the following steps:

[0045] Step S41. Determine the initial current density of the cathode and anode based on the free chlorine concentration, perform electrolysis treatment for a first time period using the initial current density, and obtain multiple real-time ammonia nitrogen concentrations at multiple time points in the electrolysis cell during the water treatment operation of the first time period.

[0046] The first time period is the initial treatment stage, during which wastewater treatment is performed based on the set control parameters. As mentioned above, the control parameter is current density, where the current density is 5 mA / cm². -2 -30mAcm -2 It is also known that there is a strong correlation between current density and free chlorine concentration. Therefore, in this embodiment, the initial current density of the cathode and anode is first determined based on the obtained free chlorine concentration, and then the electrolysis process for the first time period is performed based on this initial current density.

[0047] Step S42. Obtain the predicted concentration of ammonia nitrogen in the effluent based on the influent ammonia nitrogen concentration, the influent flow rate, and multiple real-time ammonia nitrogen concentrations.

[0048] In this embodiment, the logic for controlling the water treatment process involves obtaining the predicted concentration of ammonia nitrogen in the wastewater. This predicted concentration is used to characterize whether the current water treatment control parameters meet the emission standards. Based on the judgment result, the control parameters are then optimized under energy consumption optimization constraints to obtain the final control parameters. Therefore, to ensure the accuracy of the final control parameters, it is first necessary to obtain the predicted concentration of ammonia nitrogen in the effluent.

[0049] Due to the complexity, nonlinearity, and time-varying nature of water quality prediction in wastewater treatment, traditional prediction methods often fail to achieve ideal results. Therefore, in this embodiment, the predicted concentration of ammonia nitrogen in the effluent is obtained by constructing a prediction model. The input data for the prediction model includes the influent ammonia nitrogen concentration, the influent flow rate, and multiple real-time ammonia nitrogen concentrations. Specifically, the influent ammonia nitrogen concentration and influent flow rate are also data corresponding to multiple time points; this can be understood as the input data for the prediction model being time-series data.

[0050] Furthermore, considering the potential for high noise levels in collected data due to sensor malfunctions, human error, or other factors in specific processing scenarios, data denoising and cleaning are necessary before prediction. In this embodiment, wavelet transform is employed for denoising, specifically using the db wavelet basis function with a decomposition level of 3. This avoids redundant computation from excessively high decomposition and insufficient feature extraction from excessively low decomposition. The core of wavelet transform lies in threshold selection. In this embodiment, a dual-threshold strategy is used, combined with wavelet coefficients for segmented processing. This can be understood as setting a first and a second threshold, determining the wavelet coefficients for each input data point by performing wavelet transform on the time-series data, and then performing corresponding operations based on the threshold interval where the wavelet coefficients fall. Specifically, the input time-series data is first decomposed using the db wavelet basis function to determine the corresponding wavelet coefficients for each time-series data point. The acquired wavelet coefficients are processed using a dual-threshold strategy, with a first threshold and a second threshold. When the absolute value of the corresponding wavelet coefficient is lower than the first threshold, it is directly set to zero and considered noise data. When the absolute value of the corresponding wavelet coefficient is between the first and second thresholds, the wavelet coefficient is smoothed and compressed to reduce noise interference. When the absolute value of the corresponding wavelet coefficient is higher than the second threshold, the wavelet coefficient is kept unchanged to retain important feature information. In this embodiment, the dual-threshold wavelet coefficient processing can balance denoising and the preservation of effective information in the time series. After the threshold processing is completed, the denoised wavelet coefficients are converted into time series data through inverse wavelet transform to generate denoised input data. In this embodiment, the specific process of wavelet transform for the db wavelet basis function can be performed using existing methods, which will not be elaborated here.

[0051] For the noise-reduced data, since the difference in dimensions between different indicators is involved, the data needs to be converted. In this embodiment, the data conversion adopts normalization processing, which adopts the maximum-minimum normalization method. This method can be adopted from existing technologies and will not be described in detail in this embodiment.

[0052] The processed data from multiple indicators are input into the prediction model to obtain the predicted concentration of ammonia nitrogen in the effluent. The prediction model includes a feature extraction module, a feature fusion module, and a prediction output module. Furthermore, in this embodiment, before performing feature processing on the data, a weight needs to be assigned to each element of the input sequence. These weights represent the degree of importance given to each element in the subsequent prediction model under the current task. A larger weight indicates a more important element.

[0053] The attention score for each element is determined by using a dot product to determine the attention score between any two elements. The attention score is then converted into a normalized attention weight to ensure that the sum of all weights is 1. The input sequence is then weighted and summed according to the normalized weights to obtain the corresponding output vector, which is then used as the input to the prediction model.

[0054] In this embodiment, the feature extraction module includes a feature extraction layer corresponding to the input data, used to obtain the features corresponding to each input data sequence. Specifically, the feature extraction layer in this embodiment contains three convolutional layers, each using convolutional kernels of sizes 3, 5, and 7 to extract multi-scale features. Furthermore, each convolutional layer contains 32 filters and uses the ReLU activation function to introduce non-linear processing, and finally uses "same padding" to maintain the size of the feature data.

[0055] For each scale of features output from a convolutional layer, the output features are then pooled using max pooling layers. These pooled features are then concatenated and merged to fuse features extracted from convolutional kernels of different scales, resulting in connected features. Next, the connected features are weighted based on the attention weights corresponding to each element, amplifying the influence of important features while suppressing unimportant ones. Layer normalization is then applied to obtain the attention output. Finally, the attention machine output is flattened and features are extracted using fully connected layers. The final predicted output is obtained by applying a linear activation function to the output layer.

[0056] Step S43. Determine whether the deviation between the predicted concentration of ammonia nitrogen in the effluent and the standard concentration of ammonia nitrogen in the effluent meets the preset standard, and determine the control parameters based on the determination result.

[0057] In this embodiment, step S42 obtains the water quality prediction result of the current water treatment system. This water quality prediction result is used to characterize the future impact of the treatment effect corresponding to the current control parameters. This water quality prediction result includes two results: abnormal results and normal results. The abnormal and normal results are determined by obtaining the deviation between the two and judging whether this deviation exceeds a preset threshold range. If it exceeds the preset threshold range, it indicates that the current control parameters do not meet the water treatment requirements; if it is less than the preset threshold range, it indicates that the current control parameters can meet the water treatment requirements.

[0058] In this embodiment, meeting the water treatment requirements is the first requirement. After meeting this requirement, the control parameters need to be updated with energy consumption as a constraint to obtain the target control parameters. These target control parameters can meet the emission standards while reducing the energy consumption of the water treatment system. The control parameters are not obtained directly; instead, a set of concentrations that meet the emission standards is constructed, including multiple effluent ammonia nitrogen concentrations. Then, the effluent ammonia nitrogen concentration with the lowest energy consumption in the concentration set is determined as the target effluent concentration, and the control parameters are determined in reverse based on this target effluent concentration.

[0059] This concentration set is a key parameter for the process, and in this embodiment, it is determined by introducing historical operating data. This historical operating data includes multiple historical data sequences, each containing historical ammonia nitrogen concentration data in the electrolyzer and corresponding control parameters. The historical ammonia nitrogen concentration refers to the time-series change in ammonia nitrogen concentration in the electrolyzer during each historical treatment process; this data serves as a key indicator of the water treatment process. The historical ammonia nitrogen concentration characterizes the amount of ammonia nitrogen concentration change during historical water treatment processes, and this data serves as a key indicator of the water treatment process.

[0060] Furthermore, because water treatment processes differ under different conditions, the selection logic for control parameters also varies. Therefore, not every historical data sequence can be used to determine subsequent control parameters. Thus, it is necessary to filter historical data sequences to establish the relationship between historical and current data. Specifically, the filtering process involves calculating the similarity between the real-time data of the current treatment system and historical data sequences. Based on the similarity distribution, the association between the historical data sequences and the current treatment conditions is determined to establish a concentration set. Finally, the control parameter with the lowest energy consumption in the concentration set is used as the target control parameter.

[0061] Since step S41 has already explained that the current water treatment system processes water based on a first time period, and the corresponding real-time ammonia nitrogen concentration can be obtained within this first time period, and this real-time ammonia nitrogen concentration is highly correlated with the free chlorine concentration, the influent ammonia nitrogen concentration, and the control parameters, the sequence of real-time ammonia nitrogen concentrations can reflect the changing state of the current water treatment system. Therefore, in this embodiment, the similarity is determined based on the change in ammonia nitrogen concentration.

[0062] Furthermore, because ammonia nitrogen concentration data has a significant time dependence, in order to more accurately capture the changing patterns of dynamic features, this embodiment not only uses static similarity between data sequences for similarity calculation, but also introduces dynamic similarity based on time dependence, and combines the two to obtain a comprehensive similarity that can reflect the whole.

[0063] Specifically, static similarity is determined by calculating the similarity between real-time ammonia nitrogen concentrations and historical ammonia nitrogen concentrations at the same time point. Furthermore, since only real-time ammonia nitrogen concentration is used as the benchmark data for similarity judgment in this embodiment, in order to make the static similarity judgment more reflective of the overall similarity of the water treatment system's operating conditions, a weight of real-time ammonia nitrogen concentration in the overall operating condition data is introduced in this embodiment, and the similarity is updated based on this weight, so that the static similarity can more accurately reflect the degree of similarity between the overall water treatment systems.

[0064] In determining the weight of real-time ammonia nitrogen concentration in the overall operating data, each feature in the historical dataset is first normalized, and the information entropy corresponding to the real-time ammonia nitrogen concentration is calculated. Then, the weight is determined based on the information entropy. Normalization and information entropy acquisition can be implemented using existing methods, which will not be elaborated upon in this embodiment.

[0065] Specifically, for real-time ammonia nitrogen concentration sequences With historical data sequences The static similarity is calculated based on the following formula: Where w is the weight, This represents the maximum value from historical data.

[0066] In this embodiment, the dynamic similarity is implemented using a dynamic time warping algorithm, which involves analyzing the real-time ammonia nitrogen concentration sequence. and historical ammonia nitrogen concentration sequence ,structure Matrix, for elements express and Euclidean distance Then, the boundaries are initialized and the final distance between each data point in the two sequences is determined based on the recursive relation, where the final distance is expressed as follows: Then, based on the final distance, the dynamic similarity is determined using the following formula: ,in This represents the maximum final distance.

[0067] Finally, the static similarity and dynamic similarity are combined based on a weighted coefficient to obtain the final comprehensive similarity. In this embodiment, the weighted coefficient is 0.7, expressed by the following formula: .

[0068] In this embodiment, the above processing steps determine the similarity between the real-time ammonia nitrogen concentration sequence and each historical data sequence. The obtained similarity then needs to be used to filter multiple historical data sequences, and a concentration set is constructed based on the filtering results.

[0069] Specifically, if the similarity between a real-time ammonia nitrogen data sequence and any historical data sequence is greater than 0.95, the historical data is included in the concentration set. For this concentration set, in this embodiment, the historical energy consumption corresponding to each historical data sequence also needs to be determined. If there is only one historical data sequence in the concentration set, the ammonia nitrogen concentration at each time point in that historical data sequence is used as the set ammonia nitrogen concentration, and the control parameters in the current water treatment system are tracked and controlled based on this set ammonia nitrogen concentration. If the concentration set includes multiple historical data sequences, multiple historical energy consumption values ​​corresponding to the multiple historical data sequences are determined, and the historical data sequence with the smallest historical energy consumption value is selected as the target historical data. The ammonia nitrogen concentrations at multiple time points in the target historical data are used as the set ammonia nitrogen concentration, and the control parameters in the current water treatment system are tracked and controlled based on this set ammonia nitrogen concentration.

[0070] In this embodiment, the historical energy consumption value is calculated using historical current density data. Specifically, the corresponding historical power output value is determined based on the historical current density data, and the historical power output value is used to characterize the historical energy consumption value.

[0071] The above processing method is based on the similarity between the real-time ammonia nitrogen concentration sequence and the historical data sequence being greater than 0.95. However, if the similarity is less than 0.95, the historical data sequence cannot be directly used as the baseline data. In this case, global optimization of the historical data sequence is required to find a set ammonia nitrogen concentration that represents the optimal trade-off between water quality and energy consumption. This set ammonia nitrogen concentration is then used as the target result for the electrolysis system. Finally, similar to the above processing method, the control parameters of the current water treatment system are tracked and controlled based on this set ammonia nitrogen concentration. It's important to note that the set ammonia nitrogen concentration under the optimal trade-off condition is usually not a single optimal solution, but rather a series of solutions that cannot be further improved; these solutions are actually Pareto optimal solutions. Therefore, under this similarity condition, the optimal solution cannot be directly determined from the historical data sequence in this embodiment. Instead, the Pareto optimal solution is obtained as the final solution set, which includes the set ammonia nitrogen concentration and the corresponding control parameters.

[0072] To address the issues of high computational complexity and insufficient diversity in Pareto optimal solutions, this embodiment uses historical data sequences as the screening data for the solution set. The historical data sequences are then used as a population for iterative optimization using a genetic algorithm to determine the final Pareto solution set. Specifically, based on the fitness of multiple set ammonia nitrogen concentration values ​​in the historical data sequences, corresponding individuals are selected for crossover and mutation to generate new solutions. These new solutions replace the solutions with low fitness among the multiple solutions. This process is iterated multiple times until the maximum number of iterations is reached, and the solution with the lowest energy consumption value among the final multiple solutions is output as the optimal result. Here, the set of set ammonia nitrogen concentrations represents the effluent ammonia nitrogen concentrations in the historical data sequences, and fitness in this embodiment is similarity. This can be understood as follows: in this embodiment, the above process obtains the similarity between each historical data sequence and the real-time ammonia nitrogen concentration sequence, and the historical data with the highest similarity ranking is used as the initial population. Then, the solutions of multiple individuals in the initial population are sorted by quality through stratification, and the number of clones is selected based on the Pareto level and crowding distance of each individual. Multiple offspring populations are then generated using crossover and mutation operators. Each individual should contain two solutions: one is the energy consumption value, and the other is the set ammonia nitrogen concentration.

[0073] For each offspring population generated after the update, it is merged with its corresponding parent population to form a temporary population. The non-dominated ranking of individuals in the temporary population is obtained, and Pareto front levels are defined based on the optimal solution ranking. The crowding distance of individuals within each front layer is calculated. Then, based on the Pareto level and crowding distance, the top 50 dominant individuals are selected, and a new generation of parent population is generated based on these dominant individuals. Clonal selection, crossover, and mutation are performed on the new generation of parent population to generate corresponding new generation of offspring populations. The new generation of offspring and parent populations are then iterated again based on the above process until the maximum number of iterations is reached. The solution set in the final generation population is output. This solution set contains multiple trade-off solutions between energy consumption and effluent ammonia nitrogen concentration. The crowding distance of individuals within the front layer is determined by calculating the relative distribution density of solution individuals in the target space; the processing of this is implemented using existing technology and will not be elaborated upon in this embodiment.

[0074] In this context, optimal solution ranking refers to the ranking of the optimal solution levels corresponding to each individual. Optimal solution level refers to the dominance count and dominance set of each individual's solution. The dominance count refers to the number of other solutions that dominate the solution, and the dominance set refers to the set of other solutions dominated by the solution. Specifically, obtaining the optimal solution ranking first determines the dominance count and dominance set of each individual, and then performs a hierarchical ranking. In this embodiment, the hierarchical ranking includes three layers. The first layer filters all optimal solutions, removes all optimal solutions, and decrements the dominance relationship of other solutions by one. This process is repeated until all solutions are ranked. In the result of the three-layer ranking, the first layer represents Pareto optimal solutions, the second layer represents solutions dominated only by Pareto optimal solutions, and the third layer represents lower priority solutions.

[0075] In this embodiment, since the selected historical data set all conforms to emission standards, the effluent ammonia nitrogen concentration in the tradeoff solution also conforms to emission standards. Therefore, the final target ammonia nitrogen concentration can be directly selected from the effluent ammonia nitrogen concentration corresponding to the minimum energy consumption in the solution set. The determined target ammonia nitrogen concentration is used to track and control the control parameters. The tracking and control of the control parameters can be implemented using a PID control algorithm. Its logic is to adjust based on the deviation between the target ammonia nitrogen concentration and the current ammonia nitrogen concentration using a PID algorithm. Since this process can be directly implemented using existing PID algorithms, it will not be elaborated further in this embodiment.

[0076] Regarding the water treatment system and process control method provided in the application embodiments, an electrolytic cell with an aluminum plate as the cathode and an IrO2-RuO2 / Ti composite plate as the anode can remove ammonia nitrogen from wastewater without introducing an external carbon source. Furthermore, by incorporating a processor with energy consumption and water quality balance control within the water treatment system, key control parameters in the electrolytic cell can be adjusted using both water quality treatment results and energy consumption as constraints. This allows the water treatment system to control its energy consumption while ensuring the required effluent quality.

[0077] The technical solution provided in this application constructs a single-chamber electrolysis system based on an aluminum cathode and an IrO2-RuO2 / Ti anode for the efficient degradation of NH4+-N. This system utilizes the spontaneous pH-regulating characteristic of the aluminum cathode to automatically adjust the solution pH to a weakly alkaline state, providing optimal reaction conditions for the oxidation of NH4+-N by free chlorine. Compared to existing technologies, this reduces the risk of bioaccumulation and secondary water pollution caused by the addition of reagents. Furthermore, by obtaining water treatment prediction results, the water quality prediction results are used as the basic indicators for dynamic adjustment of the dynamic treatment process to determine multiple sets of control parameters. Energy consumption constraints are used as a screening condition to determine the parameter combination with the optimal energy consumption from these sets, and the water treatment process is controlled based on this parameter combination.

[0078] See Figure 5 The processor 30 in this embodiment specifically includes the following modules:

[0079] The data acquisition module 31 is used to determine the initial current density of the cathode and anode based on the free chlorine concentration, perform electrolysis treatment for a first time period with the initial current density, and acquire multiple real-time ammonia nitrogen concentrations at multiple time points in the electrolysis cell during the water treatment operation of the first time period.

[0080] Prediction module 32 is used to obtain the predicted concentration of ammonia nitrogen in the effluent based on the influent ammonia nitrogen concentration, the influent flow rate and multiple real-time ammonia nitrogen concentrations;

[0081] The parameter generation module 33 is used to determine whether the deviation between the predicted concentration of ammonia nitrogen in the effluent and the standard concentration of ammonia nitrogen in the effluent meets the preset standard, and to determine the control parameters based on the determination result.

[0082] See Figure 6The above methods can also be integrated into the provided terminal device 600. Since the device may vary significantly due to different configurations or performance, it may include one or more processors 601 and memories 602. The memory 602 may store one or more application programs or data. The memory 602 can be temporary or persistent storage. The application programs stored in the memory 602 may include one or more modules (not shown in the figure), each module may include a series of computer-executable instructions from the terminal device. Furthermore, the processor 601 may be configured to communicate with the memory 602, and the terminal device may execute the series of computer-executable instructions stored in the memory 602. The terminal device may also include one or more power supplies 603, one or more wired / wireless network interfaces 604, one or more input / output interfaces 605, one or more keyboards 606, etc.

[0083] In one specific embodiment, the terminal device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for use in the terminal device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following:

[0084] The initial current density of the cathode and anode is determined based on the free chlorine concentration. Electrolysis is performed for a first time period using the initial current density, and multiple real-time ammonia nitrogen concentrations at multiple time points in the electrolysis cell during the water treatment operation of the first time period are obtained.

[0085] The predicted concentration of ammonia nitrogen in the effluent is obtained based on the influent ammonia nitrogen concentration, the influent flow rate, and multiple real-time ammonia nitrogen concentrations.

[0086] Determine whether the deviation between the predicted concentration of ammonia nitrogen in the effluent and the standard concentration of ammonia nitrogen in the effluent meets the preset standard, and determine the control parameters based on the determination result.

[0087] Optionally, the processor can perform various functions, such as the above-mentioned functions, by running or executing software programs stored in memory and by calling data stored in memory. Figure 4 The method shown.

[0088] In a specific implementation, as one example, the processor may include one or more microprocessors.

[0089] The memory is used to store the software program that executes the solution of this application, and the execution is controlled by the processor. The specific implementation method can be referred to the above method embodiment, which will not be repeated here.

[0090] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0091] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0092] Those skilled in the art will recognize that the units 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 design 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.

[0093] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0094] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0095] 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.

Claims

1. A water treatment system for denitrifying wastewater, characterized in that, include: The system comprises a processing device, a control device, and a processor. The processing device is an electrolytic cell equipped with multiple sensors. These sensors acquire various types of detection data from multiple regions within the electrolytic cell and transmit the data to the processor. The processor determines the deviation between the current system's operating state and its optimal state based on the detection data, determines control parameters based on the deviation, and sends these parameters to the control device. The deviation includes deviations in effluent ammonia nitrogen concentration and energy consumption. The electrolytic cell contains an electrolysis assembly, which includes a parallel cathode and anode, and a DC power supply connected to the cathode and anode. The cathode is an aluminum-containing metal plate, and the anode is an IrO2-RuO2 / Ti composite plate. The detection data includes free chlorine concentration, influent ammonia nitrogen concentration, influent flow rate, and real-time ammonia nitrogen concentration.

2. A water treatment process control method, characterized in that, The method is applied to a processor in the water treatment system of claim 1, and the method includes: The initial current density of the cathode and anode is determined based on the free chlorine concentration. Electrolysis is performed for a first time period using the initial current density, and multiple real-time ammonia nitrogen concentrations at multiple time points in the electrolysis cell are obtained during the water treatment operation of the first time period. The predicted concentration of ammonia nitrogen in the effluent is obtained based on the influent ammonia nitrogen concentration, the influent flow rate, and multiple real-time ammonia nitrogen concentrations. Determine whether the deviation between the predicted concentration of ammonia nitrogen in the effluent and the standard concentration of ammonia nitrogen in the effluent meets the preset standard, and determine the control parameters based on the determination result.

3. The water treatment process control method according to claim 2, characterized in that, The control parameters are determined based on the judgment results, including: when the deviation does not meet the preset standard, updating the initial current density in the electrolytic cell according to the degree of the deviation, performing water treatment operation based on the second time, and determining whether the deviation between the predicted concentration of ammonia nitrogen in the effluent and the standard concentration of ammonia nitrogen in the effluent at the second time meets the preset standard based on the operation process.

4. The water treatment process control method according to claim 2 or 3, characterized in that, When the deviation meets the preset standard, multiple concentration sets are obtained; and the target ammonia nitrogen concentration is obtained by screening the multiple concentration sets with energy consumption as a constraint, and the real-time current density is dynamically adjusted based on the target ammonia nitrogen concentration.

5. The water treatment process control method according to claim 4, characterized in that, Obtaining multiple concentration sets includes: obtaining a historical data set, calculating the similarity between real-time data and the historical data set, and determining associated concentration sets based on the similarity distribution; the historical data set includes multiple historical datasets, each of which includes historical influent flow rate, historical influent ammonia nitrogen concentration, and historical current density; calculating the similarity between real-time data and the historical data set includes: calculating the similarity between real-time ammonia nitrogen concentration and the historical ammonia nitrogen concentration of each of the historical datasets to obtain the similarity between real-time data and each of the historical datasets.

6. The water treatment process control method according to claim 5, characterized in that, Determining an associated concentration set based on similarity distribution includes: determining the similarity value between the real-time data and multiple historical datasets, and selecting historical datasets with similarity values ​​greater than a first preset value as the associated concentration set; when the similarity value is less than the first preset value, selecting historical datasets with similarity values ​​greater than a second preset value as the basic associated concentration set, and performing optimization processing on the basic associated concentration set to obtain the associated concentration set.

7. The water treatment process control method according to claim 6, characterized in that, The method of selecting a target ammonia nitrogen concentration by filtering multiple concentration sets with energy consumption as a constraint includes: obtaining historical current density data corresponding to each historical dataset in multiple concentration sets, determining the corresponding historical energy consumption based on the historical current density data, selecting the historical dataset with the lowest historical energy consumption as the target historical dataset, and the effluent ammonia nitrogen concentration in the target historical dataset as the target ammonia nitrogen concentration.

8. The water treatment process control method according to claim 2, characterized in that, The method for obtaining the predicted concentration of ammonia nitrogen in the effluent based on the influent ammonia nitrogen concentration, the influent flow rate, and multiple real-time ammonia nitrogen concentrations includes: obtaining multiple features corresponding to the influent ammonia nitrogen concentration, the influent flow rate, and multiple real-time ammonia nitrogen concentrations respectively; connecting the multiple features and updating the connected features based on the weight corresponding to each feature to obtain an attention output; and obtaining the prediction result based on the attention output.

Images