A method for recovering ammonia nitrogen from wastewater by transmembrane pulse electrochemistry based on machine learning

Through machine learning, optimize the pulse duty cycle of the transmembrane pulse electrochemical system has been solved, and the problem of high energy consumption in the existing technology has been achieved, low energy consumption and high efficiency ammonia nitrogen recovery is achieved, and it is suitable for wastewater treatment.

CN119417459BActive Publication Date: 2025-09-02TONGJI UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411435542.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-10-15
Publication Date
2025-09-02
Estimated Expiration
2044-10-15

AI Technical Summary

Technical Problem

The existing transmembrane pulse electrochemical method for recycling wastewater nitrogen and nitrogen is difficult to reduce energy consumption while ensuring high efficiency, and it is difficult to effectively control the pulse duty cycle of ammonia nitrogen recovery in each period.

Method used

Combining machine learning and transmembrane pulse electrochemical system, through a pre-trained ammonia nitrogen recovery efficiency prediction model, the pulse duty cycle configuration is optimized, and the optimal pulse duty cycle configuration information is selected to achieve low energy consumption and high efficiency ammonia nitrogen recovery.

Benefits of technology

It realizes efficient recycling of ammonia nitrogen in sewage under low energy consumption, improves the recycling efficiency of ammonia nitrogen in sewage, reduces energy consumption, and is suitable for actual sewage treatment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119417459B_ABST
    Figure CN119417459B_ABST
Patent Text Reader

Abstract

An embodiment of the present invention provides a method for recovering ammonia nitrogen from wastewater by transmembrane pulse electrochemistry based on machine learning, including: obtaining the pulse frequency, applied voltage, cathode liquid initial concentration, anode liquid initial concentration, and brine initial concentration required for recovering ammonia nitrogen from target wastewater using a transmembrane pulse electrochemical system; for any pulse duty cycle configuration information input by the user, inputting it together with the pulse frequency, applied voltage, cathode liquid initial concentration, etc. into a pre-trained ammonia nitrogen recovery efficiency prediction model to obtain corresponding ammonia nitrogen recovery efficiency information; based on the ammonia nitrogen recovery efficiency information corresponding to multiple pulse duty cycle configuration information, selecting the pulse duty cycle configuration information with an ammonia nitrogen removal efficiency and an ammonia nitrogen recovery efficiency that are not less than the corresponding preset thresholds, and with the minimum ammonia nitrogen recovery energy consumption; based on the selected pulse duty cycle configuration information and the pulse frequency, applied voltage, cathode liquid initial concentration, etc., using the transmembrane pulse electrochemical system to recover ammonia nitrogen from the target wastewater.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of environmental engineering technology, and in particular to a method for recovering ammonia nitrogen from sewage by transmembrane pulse electrochemistry based on machine learning. Background Art

[0002] Ammonia (NH3) is a high-energy-density energy storage / conversion carrier. The increasing global population and industrialization are leading to an increasing demand for ammonia. Currently, ammonia production relies primarily on the energy-intensive Haber-Bosch (HB) process, which consumes 1-2% of the world's energy annually and accounts for 1.4% of global carbon emissions. At the same time, the massive ammonia consumption driven by increased demand has also led to a continuous increase in nitrogen content in wastewater, exacerbating eutrophication of water bodies. In the context of dual carbon, recycling ammonia nitrogen from wastewater can effectively utilize ammonia nitrogen as a resource.

[0003] Ammonia can be recovered from wastewater through a series of methods, including gas stripping, chemical precipitation, ion exchange / adsorption, and capacitive deionization. However, all of the above methods have some defects, such as the need to heat the influent, the additional addition of chemicals, low ammonia recovery selectivity and efficiency, and the difficulty in scaling up the reactor. The electrochemical method for removing ammonia has the characteristics of simple operation and no secondary pollution, and has obvious advantages in treating high-ammonia nitrogen wastewater. Among them, transmembrane electrochemical absorption technology (TMECS) is increasingly popular because it does not require an additional stripping step, thereby reducing the complexity of the reactor and easily increasing the processing capacity by scaling up and stacking. However, the above studies all have the problem of high energy consumption, which limits their promotion and application. Pulse technology is expected to reduce energy consumption due to the reduction of the total discharge time, and can also alleviate the H generated by the electrolysis of water on the surface of the electrodes in the anode and cathode chambers. + and OH - The accumulation of a diffusion layer reduces the energy consumption generated by the overpotential. Therefore, the low energy consumption of pulsed power supplies, combined with the advantages of TMECS and pulsed electric fields, is used to achieve low-cost, low-energy, and high-efficiency recovery of ammonia from wastewater. However, when using transmembrane pulse electrochemical technology to recover ammonia nitrogen from wastewater, it is currently difficult to control the pulse duty cycle of each time period to achieve a level that meets the recovery efficiency requirements while maintaining low energy consumption. Summary of the Invention

[0004] In a first aspect, an embodiment of the present invention provides a method for recovering ammonia nitrogen from wastewater by transmembrane pulse electrochemistry based on machine learning, the method comprising:

[0005] Obtain the pulse frequency, applied voltage, catholyte initial concentration, anolyte initial concentration, and brine initial concentration required for ammonia nitrogen recovery from target wastewater using a transmembrane pulse electrochemical system;

[0006] Receive multiple different pulse duty cycle configuration information for target sewage input by the user, wherein one pulse duty cycle configuration information is used to represent the pulse duty cycle configured in each time period during the ammonia nitrogen recovery of the target sewage using the transmembrane pulse electrochemical system;

[0007] For any pulse duty cycle configuration information, input it, along with the pulse frequency, applied voltage, initial cathode liquid concentration, initial anolyte concentration, and initial brine concentration, into a pre-trained ammonia nitrogen recovery efficiency prediction model to obtain the ammonia nitrogen recovery efficiency information corresponding to the pulse duty cycle configuration information. The ammonia nitrogen recovery efficiency includes ammonia nitrogen removal efficiency, ammonia nitrogen recovery efficiency, and ammonia nitrogen recovery specific energy consumption.

[0008] Based on the ammonia nitrogen recovery efficiency information corresponding to the multiple pulse duty cycle configuration information, select the pulse duty cycle configuration information with the ammonia nitrogen removal efficiency and the ammonia nitrogen recovery efficiency not less than the corresponding preset thresholds and the minimum ammonia nitrogen recovery specific energy consumption from the multiple pulse duty cycle configuration information;

[0009] Based on the selected pulse duty cycle configuration information as well as the pulse frequency, applied voltage, initial cathode liquid concentration, initial anode liquid concentration, and initial brine concentration, a transmembrane pulse electrochemical system is used to recover ammonia nitrogen from the target wastewater.

[0010] In some implementations of the first aspect, the output voltage of the pulse power supply in the transmembrane pulse electrochemical system is 0-1000V, the output current is 0-9000A, the output power is 0-9000KVA, the frequency range is 0.1-50000HZ, and the duty cycle range is 0-100%.

[0011] In some implementations of the first aspect, the chambers in the transmembrane pulse electrochemical system include a cathode chamber, an anode chamber, two desalination chambers, a sub-cathode chamber, and a sub-anode chamber;

[0012] The auxiliary cathode chamber is connected to its corresponding desalination chamber by a cation exchange membrane, the auxiliary anode chamber is connected to its corresponding desalination chamber by an anion exchange membrane, and the cathode chamber and the anode chamber are connected by a gas-permeable and hydrophobic membrane;

[0013] The auxiliary anode is an iridium-tantalum-titanium anode, and the auxiliary cathode is a stainless steel wire mesh.

[0014] In some implementations of the first aspect, the ammonia nitrogen recovery efficiency prediction model is trained by the following steps:

[0015] Acquire data from ammonia nitrogen recovery experiments using a transmembrane pulse electrochemical system and construct a dataset based on this data;

[0016] The sample data in the dataset include: pulse duty cycle configured in each time period during the ammonia nitrogen recovery experiment, pulse frequency, applied voltage, initial cathode liquid concentration, initial anode liquid concentration, initial brine concentration, cathode liquid concentration, and anode liquid concentration; the label data in the dataset include: ammonia nitrogen removal efficiency, ammonia nitrogen recovery efficiency, and ammonia nitrogen recovery specific energy consumption during the ammonia nitrogen recovery experiment;

[0017] The initial neural network was trained according to the data set to obtain an ammonia nitrogen recovery efficiency prediction model.

[0018] In some implementations of the first aspect, an initial neural network is trained based on a data set to obtain an ammonia nitrogen recovery efficiency prediction model, including:

[0019] Normalize the data in the dataset and divide the normalized dataset into a training set and a test set;

[0020] The initial neural network is trained using the training set, and at the end of the training, the performance of the current neural network is tested using the test set. If the performance test is passed, the current neural network is used as an ammonia nitrogen recovery efficiency prediction model.

[0021] In some implementations of the first aspect, using the training set to train the initial neural network includes:

[0022] Input the sample data in the training set into the initial neural network to obtain the output result, calculate the error between the output result and the label data, update the model parameters of the neural network according to the error, and continuously iterate and update until the preset stopping condition is met.

[0023] In some implementations of the first aspect, the neural network is a back propagation neural network (BPNN).

[0024] In a second aspect, an embodiment of the present invention provides a device for recovering ammonia nitrogen from wastewater by transmembrane pulse electrochemistry based on machine learning, the device comprising:

[0025] An acquisition module is used to obtain the pulse frequency, applied voltage, catholyte initial concentration, anolyte initial concentration, and brine initial concentration required for recovering ammonia nitrogen from target wastewater using a transmembrane pulse electrochemical system;

[0026] A receiving module is used to receive multiple different pulse duty cycle configuration information for target sewage input by a user, wherein one pulse duty cycle configuration information is used to represent the pulse duty cycle configured in each time period during the ammonia nitrogen recovery of the target sewage using the transmembrane pulse electrochemical system;

[0027] A prediction module is used to input any pulse duty cycle configuration information, along with the pulse frequency, applied voltage, cathode liquid initial concentration, anolyte initial concentration, and brine initial concentration, into a pre-trained ammonia nitrogen recovery efficiency prediction model to obtain ammonia nitrogen recovery efficiency information corresponding to the pulse duty cycle configuration information, wherein the ammonia nitrogen recovery efficiency includes ammonia nitrogen removal efficiency, ammonia nitrogen recovery efficiency, and ammonia nitrogen recovery specific energy consumption;

[0028] A selection module is used to select, based on the ammonia nitrogen recovery efficiency information corresponding to the multiple pulse duty cycle configuration information, the pulse duty cycle configuration information with the ammonia nitrogen removal efficiency and the ammonia nitrogen recovery efficiency being not less than the corresponding preset thresholds and the minimum ammonia nitrogen recovery specific energy consumption from the multiple pulse duty cycle configuration information;

[0029] The recovery module is used to recover ammonia nitrogen from the target wastewater using a transmembrane pulse electrochemical system based on the selected pulse duty cycle configuration information and pulse frequency, applied voltage, initial cathode liquid concentration, initial anode liquid concentration, and initial brine concentration.

[0030] In a third aspect, an embodiment of the present invention provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described above.

[0031] In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to enable a computer to execute the method described above.

[0032] In an embodiment of the present invention, machine learning can be combined with transmembrane pulse electrochemical recovery of ammonia nitrogen from wastewater, and a prediction model can be introduced to predict the ammonia nitrogen recovery efficiency of the transmembrane pulse electrochemical system. Based on the prediction results, the pulse duty cycle of the ammonia nitrogen recovery in each time period can be controlled to achieve a level that can meet the recovery efficiency requirements while maintaining low energy consumption, thereby improving the ammonia nitrogen recovery efficiency of wastewater.

[0033] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The above and other features, advantages, and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are provided for a better understanding of the present invention and do not constitute a limitation of the present invention. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0035] Figure 1 A flow chart of a method for recovering ammonia nitrogen from wastewater by transmembrane pulse electrochemistry based on machine learning provided in an embodiment of the present invention;

[0036] Figure 2 This is a structural diagram of the transmembrane pulse electrochemical system;

[0037] Figure 3 Schematic diagram of ammonia nitrogen removal efficiency and ammonia nitrogen recovery efficiency under different reaction conditions in the process of treating ammonia nitrogen wastewater;

[0038] Figure 4 Schematic diagram of specific energy consumption for ammonia nitrogen recovery under different reaction conditions in the process of treating nitrogen-containing wastewater;

[0039] Figure 5 A flow chart for building an ammonia nitrogen recovery efficiency prediction model based on BPNN;

[0040] Figure 6 is R under different numbers of hidden layers and different numbers of hidden neurons 2 and RMSE value;

[0041] Figure 7 A diagram showing strategies for improving the efficiency of ammonia nitrogen recovery from simulated urine using a transmembrane pulse electrochemical system;

[0042] Figure 8 This is a comparison chart of ammonia nitrogen removal and recovery efficiency under direct current conditions and boosting strategy;

[0043] Figure 9 This is a comparison chart of energy consumption of ammonia nitrogen recovery under DC conditions and boosting strategy;

[0044] Figure 10 A structural diagram of a device for recovering ammonia nitrogen from wastewater using transmembrane pulse electrochemical technology based on machine learning, provided in an embodiment of the present invention;

[0045] Figure 11 A structural diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0047] In addition, the term "and / or" in this invention merely describes an association relationship between related objects, indicating that three possible relationships exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Furthermore, the character " / " in this invention generally indicates that the related objects are in an "or" relationship.

[0048] In order to solve the technical problems arising from the background technology, the embodiments of the present invention provide a method, device, equipment and storage medium for recovering ammonia nitrogen from sewage by transmembrane pulse electrochemistry based on machine learning. Specifically, the pulse frequency, applied voltage, initial concentration of cathode liquid, initial concentration of anode liquid and initial concentration of brine required for recovering ammonia nitrogen from target sewage using a transmembrane pulse electrochemical system are obtained; for any pulse duty cycle configuration information input by the user, it is input into a pre-trained ammonia nitrogen recovery efficiency prediction model together with the pulse frequency, applied voltage, initial concentration of cathode liquid, etc. to obtain the corresponding ammonia nitrogen recovery efficiency information; based on the ammonia nitrogen recovery efficiency information corresponding to the multiple pulse duty cycle configuration information, the pulse duty cycle configuration information with ammonia nitrogen removal efficiency and ammonia nitrogen recovery efficiency not less than the corresponding preset thresholds and the minimum energy consumption of ammonia nitrogen recovery ratio is selected; based on the selected pulse duty cycle configuration information and the pulse frequency, applied voltage, initial concentration of cathode liquid, etc., the transmembrane pulse electrochemical system is used to recover ammonia nitrogen from the target sewage.

[0049] In this way, machine learning can be combined with transmembrane pulse electrochemical recovery of ammonia nitrogen from wastewater, and a prediction model can be introduced to predict the ammonia nitrogen recovery efficiency of the transmembrane pulse electrochemical system. Based on the prediction results, the pulse duty cycle of ammonia nitrogen recovery in each time period can be controlled to achieve a level that can meet the recovery efficiency requirements while maintaining low energy consumption, thereby improving the ammonia nitrogen recovery efficiency of wastewater.

[0050] Below, in conjunction with the accompanying drawings, a method, device, equipment and storage medium for recovering ammonia nitrogen from wastewater by transmembrane pulse electrochemistry based on machine learning provided by an embodiment of the present invention are described in detail through specific embodiments.

[0051] Figure 1 A flow chart of a method for recovering ammonia nitrogen from wastewater by transmembrane pulse electrochemistry based on machine learning is provided in an embodiment of the present invention, such as Figure 1 As shown, the method 100 may include the following steps:

[0052] S110, obtaining the pulse frequency, applied voltage, cathode liquid initial concentration, anode liquid initial concentration, and brine initial concentration required for recovering ammonia nitrogen from target wastewater using a transmembrane pulse electrochemical system.

[0053] Among them, the structure of the transmembrane pulse electrochemical system can be as follows Figure 2As shown, the chambers in the transmembrane pulse electrochemical system include a cathode chamber, an anode chamber, two desalination chambers, a sub-cathode chamber, and a sub-anode chamber, and can be amplified by stacking. The sub-cathode chamber is connected to its corresponding desalination chamber by a cation exchange membrane, the sub-anode chamber is connected to its corresponding desalination chamber by an anion exchange membrane, the cathode chamber and the anode chamber are connected by a breathable hydrophobic membrane, the (sub-) anode uses an iridium tantalum titanium anode, and the (sub-) cathode uses a stainless steel wire mesh. The output voltage of the pulse power supply in the transmembrane pulse electrochemical system is 0-1000V, the output current is 0-9000A, the output power is 0-9000KVA, the frequency range is 0.1-50000HZ, and the duty cycle range is 0-100%.

[0054] S120: Receive multiple different pulse duty cycle configuration information for target sewage input by the user.

[0055] Each pulse duty cycle configuration information is used to represent the pulse duty cycle configured for each time period during the ammonia nitrogen recovery of the target wastewater using the transmembrane pulse electrochemical system. For example, if the ammonia nitrogen recovery period is 0-10 hours, there are five time periods: 0-2 hours, 2-4 hours, 4-6 hours, 6-8 hours, and 8-10 hours. In this case, a pulse duty cycle configuration information can be 0-2 hours, 63%; 2-4 hours, 50%; 4-6 hours, 44%; 6-8 hours, 38%; 8-10 hours, 25%.

[0056] S130, for any pulse duty cycle configuration information, input it together with the pulse frequency, external voltage, cathode liquid initial concentration, anode liquid initial concentration, and brine initial concentration into a pre-trained ammonia nitrogen recovery efficiency prediction model to obtain the ammonia nitrogen recovery efficiency information corresponding to the pulse duty cycle configuration information.

[0057] Among them, ammonia nitrogen recovery efficiency includes ammonia nitrogen removal efficiency, ammonia nitrogen recovery efficiency, and ammonia nitrogen recovery specific energy consumption. The above ammonia nitrogen recovery efficiency prediction model can be trained through the following steps:

[0058] A dataset was constructed using data from ammonia nitrogen recovery experiments using a transmembrane pulse electrochemical system. Sample data in the dataset includes the pulse duty cycle configured for each time period during the ammonia nitrogen recovery experiment, the pulse frequency, applied voltage, initial catholyte concentration, initial anolyte concentration, initial brine concentration, catholyte concentration, and anolyte concentration. Label data in the dataset includes the ammonia nitrogen removal efficiency, ammonia nitrogen recovery efficiency, and specific energy consumption for ammonia nitrogen recovery during the experiment.

[0059] An initial neural network (e.g., a BPNN) is trained based on the dataset to obtain an ammonia nitrogen recovery efficiency prediction model. Specifically, the data in the dataset is normalized and divided into a training set and a test set according to a preset ratio, such as (3:2). The initial neural network is trained using the training set. At the end of the training, the performance of the current neural network is tested using the test set. If the performance test is passed, the current neural network is used as the ammonia nitrogen recovery efficiency prediction model.

[0060] For example, the training of the initial neural network using the training set can be performed as follows:

[0061] The sample data in the training set is input into the initial neural network to obtain the output result, the error between the output result and the label data is calculated, and the model parameters of the neural network are updated according to the error. The update is continued iteratively until the preset stopping condition is met (for example, the error is less than the preset threshold or the number of iterations reaches the preset threshold).

[0062] S140, based on the ammonia nitrogen recovery efficiency information corresponding to multiple pulse duty cycle configuration information, select the pulse duty cycle configuration information from the multiple pulse duty cycle configuration information, in which the ammonia nitrogen removal efficiency and the ammonia nitrogen recovery efficiency are not less than the corresponding preset thresholds, and the ammonia nitrogen recovery ratio energy consumption is minimized.

[0063] That is to say, here, based on the ammonia nitrogen recovery efficiency information corresponding to multiple pieces of pulse duty cycle configuration information, the pulse duty cycle configuration information that optimizes the ammonia nitrogen recovery efficiency is selected from the multiple pieces of pulse duty cycle configuration information.

[0064] S150, based on the selected pulse duty cycle configuration information and pulse frequency, applied voltage, cathode liquid initial concentration, anode liquid initial concentration, and brine initial concentration, a transmembrane pulse electrochemical system is used to recover ammonia nitrogen from the target wastewater.

[0065] Specifically, based on the selected pulse duty cycle configuration information as well as the pulse frequency, applied voltage, initial cathode liquid concentration, initial anode liquid concentration, and initial brine concentration, the transmembrane pulse electrochemical system is configured accordingly, and the configured transmembrane pulse electrochemical system is used to recover ammonia nitrogen from the target wastewater.

[0066] To facilitate further understanding, the above content is described in detail below with reference to some specific embodiments:

[0067] Example 1:

[0068] The structure of the transmembrane pulse electrochemical system involved in the present invention is as follows Figure 2As shown, the chamber consists of a cathode chamber, an anode chamber, a desalination chamber, a secondary cathode chamber, and a secondary anode chamber, and can be amplified through stacking. The secondary cathode chamber is connected to its corresponding desalination chamber by a cation exchange membrane, the secondary anode chamber is connected to its corresponding desalination chamber by an anion exchange membrane, and the cathode chamber and anode chamber are connected by a gas-permeable and hydrophobic membrane. The secondary anode is an iridium-tantalum-titanium anode (4.0 cm × 4.0 cm), and the secondary cathode is a stainless steel wire mesh (200 mesh, 0.1 mm thick, 4.0 cm × 4.0 cm, model 304). The cation exchange membrane (4.0 cm × 4.0 cm) used in the system is CMI-7000, the anion exchange membrane (4.0 cm × 4.0 cm) is AMI-7001, and the gas-permeable and hydrophobic membrane (4.0 cm × 4.0 cm) is made of polytetrafluoroethylene with a polypropylene support layer. The cathode chamber is injected with simulated ammonia nitrogen wastewater (120 mL) prepared with deionized water containing varying concentrations of ammonium sulfate. Ammonium sulfate solutions of different concentrations (120 mL) were injected into the anode chamber. 150 mM sodium sulfate solution (120 mL) was injected into each of the two desalination chambers. Sodium sulfate solutions of different concentrations (120 mL) were injected into the sub-cathode chamber and the sub-anode chamber. Experiments were conducted to explore the various factors that affect the system's ammonia nitrogen recovery effect and energy efficiency, which are mainly divided into two categories: solution parameter settings of each chamber in the reaction system (cathode liquid concentration, anode liquid concentration, brine concentration in the desalination chamber) and pulse power supply parameter settings (pulse duty cycle, pulse frequency, applied voltage). During the factor experiment, the reactor settings, system operation mode, and solution components of each chamber remained unchanged. The test cycle was 10 h, the sampling time interval was 2 h, the sampling volume was 1 mL each time, and the pH of each chamber was measured and recorded. All experiments were carried out under a temperature of 25 ± 1 ° C. The specific experimental settings and methods are as follows:

[0069] (1) The initial experimental conditions are: the simulated sewage components and concentration in the cathode chamber are 3000 mg NH4 + -N / L (NH4)2SO4+3000mg / L Na2SO4, the concentration of the anode chamber solution is 168mg NH4 + The reactor was filled with 100-N / L (NH₄)₂SO₄, 150 mM Na₂SO₄ in the secondary cathode and secondary anode chambers, and 500 mM Na₂SO₄ in the two desalination chambers. The two chambers were connected by an external hose for brine circulation at a rate of 25 mL / min. The system circuit was connected in series, with the power supply connected to the reactor's secondary cathode and secondary anode. A pulsed power supply (SOYI-1506M) provided power to the system at a 50% duty cycle. The duty cycle was adjusted to 100% for DC power supply, maintaining constant voltage operation.

[0070] (2) In the experiment to investigate the effect of cathode liquid concentration on the recovery rate and energy efficiency of the transmembrane pulse electrochemical system, except for changing the (NH4)2SO4 concentration in the cathode chamber solution, the other conditions were kept consistent with the pulse group in the feasibility experiment. In the subsequent factor experiment, except for the individual factors to be investigated, the other conditions were also kept consistent with the pulse group in the feasibility experiment. The corresponding NH4 in the cathode liquid in this study + -N concentration is set to 1000, 2000, 3000, 4000, 5000 mg NH4 + -N / L.

[0071] (3) In the experiment to explore the effect of duty cycle on the recovery rate and energy efficiency of the transmembrane pulse electrochemical system, the duty cycle was set to 0%, 20%, 40%, 50%, 60%, 80%, and 100%.

[0072] (4) In the experiment to explore the effect of voltage on the recovery rate and energy efficiency of the transmembrane pulse electrochemical system, the external voltage was set to 0V, 3V, 6V, 9V, 12V, and 15V.

[0073] (5) In the experiment to investigate the effect of pulse frequency on the recovery rate and energy efficiency of the transmembrane pulse electrochemical system, the pulse frequency was set to 50 Hz, 1500 Hz, 3000 Hz, 4500 Hz, and 6000 Hz.

[0074] (6) In the experiment to investigate the effect of anolyte concentration on the recovery rate and energy efficiency of the transmembrane pulse electrochemical system, the concentration of (NH4)2SO4 in the anolyte was set to 6mM, 12mM, 18mM, 24mM, 30mM, and 50mM;

[0075] (7) In order to investigate the effect of the saline concentration in the desalination chamber on the recovery rate and energy efficiency of the transmembrane pulse electrochemical system, the concentration of Na2SO4 in the desalination chamber was set to 150mM, 200mM, 300mM, 400mM, and 500mM.

[0076] The ammonia removal efficiency and recovery efficiency under different reaction conditions in the treatment of nitrogen-containing wastewater are as follows: Figure 3 As shown, the corresponding specific energy consumption is Figure 4 shown.

[0077] When the duty cycle is >20%, the removal rate and recovery rate of the system can reach more than 90% and more than 75% respectively after 10 hours of operation. The specific energy consumption of the system is low at low duty cycles, but the reaction time needs to be extended to achieve a removal rate and recovery rate close to that of high duty cycles. Therefore, it has better application prospects to choose a suitable duty cycle according to the specific needs of reaction speed and energy consumption. In contrast, the change of frequency has almost no effect on the ammonia removal and recovery of this system. The ammonia removal and recovery effect improves with the increase of voltage, and at the same time, the corresponding specific energy consumption also increases. NH4 in the anode liquid + Increasing concentration reduces the chemical potential difference with the adjacent cathode chamber, leading to a gradual decrease in ammonia recovery efficiency. This system exhibits good treatment capabilities for wastewater with a wide range of ammonia nitrogen concentrations. After 10 hours, when the cathode liquid ammonia nitrogen concentrations were 1000 mg / L, 3000 mg / L, and 5000 mg / L, the ammonia removal efficiencies were 96.7%, 94.4%, and 92.5%, respectively. Ammonia recovery efficiencies were 73.8%, 81.4%, and 76.0%, respectively. The corresponding specific energy consumptions were 100.3 kWh / kg N, 28.5 kWh / kg N, and 20.0 kWh / kg N, respectively.

[0078] Example 2:

[0079] This article provides a method for building an ammonia nitrogen recovery efficiency prediction model based on BPNN to predict ammonia nitrogen recovery efficiency. The construction of the ammonia nitrogen recovery efficiency prediction model is divided into the following three parts: data preparation, network construction, and model training.

[0080] In terms of data preparation, the data source is the experimental data in Example 1, and each set of data includes pulse duty cycle, pulse frequency, applied voltage, cathode liquid initial concentration, anolyte initial concentration, brine initial concentration, cathode liquid concentration, anolyte concentration, pH, ammonia nitrogen removal rate, ammonia nitrogen recovery rate, and ammonia nitrogen recovery ratio energy consumption. A data set is constructed based on this data, and the sample data in the data set include: pulse duty cycle, pulse frequency, applied voltage, cathode liquid initial concentration, anolyte initial concentration, brine concentration, cathode liquid concentration, anolyte concentration, and pH; the label data in the data set include: ammonia nitrogen removal efficiency, ammonia nitrogen recovery efficiency, and ammonia nitrogen recovery ratio energy consumption. The data in the data set are normalized, and the normalized data set is divided into a training set and a test set according to a preset ratio, for example, (3:2).

[0081] In the process of building the ammonia nitrogen recovery efficiency prediction model, it is necessary to complete the network structure initialization, randomly initialize the weights, set the activation function, set the learning rate and the number of iterations. After the data preprocessing and model building are completed, the training set is used to train the model. The training process of data in the neural network is mainly divided into the forward propagation process and the back propagation process. During the forward propagation process, the data is input into the neural network, passes through the hidden layer and the output layer in sequence, and the error between the output result and the label data is calculated. Then it enters the back propagation stage, in which the model adjusts the weights of each parameter and updates the weights. Then repeat the above process until the error between the output result and the actual result reaches the target, and then use the test set to perform a performance test on the current model. If it passes the performance test, the current model will be used as the final ammonia nitrogen recovery efficiency prediction model. The flow chart is as follows Figure 5 shown.

[0082] The models and software used are all run in a Windows 10 system environment. The computer language used is Python, and the integrated development environment (IDE) is PyCharm 2024.1 (Community Edition). The model runs based on the PyTorch deep learning framework. Anaconda 3 is used to configure the environment and manage toolkits. The toolkits used mainly include scikit-learn, numpy, scipy, pandas, etc. During the model training process, the data prediction values ​​and corresponding model parameters are automatically written to Excel tables for storage. The specific code construction process of the BPNN-based ammonia nitrogen recovery efficiency prediction model is as follows:

[0083] Import the required libraries and modules → Define the model → Set the global seed → Read the data → Set the parameters → Use the function to set the seed → Dataset processing → Separate features and labels → Divide the training set and test set → Data normalization → Convert to PyTorch tensors → Model initialization → Define the optimizer and loss function → Set early stopping parameters → Write storage parameters → Model training → Model prediction → Calculate R 2 and RMSE → Check if the performance has improved → Check if it has reached the pre-set threshold → Record R 2 and RMSE and write to file → End.

[0084] After the model is built, data reading and model training are performed. Data reading is done by saving the existing experimental data and the parameters corresponding to the experimental results to be predicted in a csv format file in a specific folder path. After clicking the run button in the PyCharm software, the model starts running, automatically reading the data file and performing data training and prediction. The predicted results and the corresponding R 2After the model prediction is completed, parameters such as RMSE will be displayed in the PyCharm software. At the same time, all prediction data will be automatically generated by the model into a CSV format file and saved in the same folder with a custom name.

[0085] In the above process, the main parameters involved are feature dimension, number of neural network layers, number of hidden layer neurons, label dimension, training rounds, and training set test set ratio. 2 and RMSE are used as the accuracy evaluation indicators of the model. Figure 6 Shows R under different numbers of hidden layers and different numbers of hidden neurons 2 And RMSE value. The experiment obtained better R when the number of hidden layers was 1. 2 Except for the RMSE value, as the number of hidden layers increases, the model accuracy cannot be improved. As the number of neurons in the hidden layer increases, the model has the best R when the number of neurons is 8. 2 (0.953) and RMSE (7.606). Therefore, in subsequent studies, the number of hidden layers and the number of hidden layer neurons were set to 1 and 8, respectively.

[0086] Example 3:

[0087] Source-separated urine is used as the practical application object of the transmembrane pulse electrochemical system for recovering ammonia nitrogen from wastewater. The ammonia nitrogen recovery efficiency prediction model trained in Example 2 is used to predict the ammonia nitrogen recovery efficiency of actual urine, and compared with the ammonia nitrogen recovery efficiency under direct current conditions to verify the ammonia nitrogen recovery efficiency advantage of this transmembrane pulse electrochemical system over the direct current system.

[0088] The collected urine was stored in a sealed brown reagent bottle and placed in a cool environment at room temperature. After the urine was naturally hydrolyzed for 30 days, its ammonia nitrogen content was determined. The ammonia nitrogen content was approximately 4750 mg NH4 + -N / L. The urine hydrolyzate that had been hydrolyzed for 30 days was used as the cathode chamber solution. The specific experimental setting conditions were as follows: 120 mL of 150 mM Na2SO4 solution was added to the sub-cathode chamber and the sub-anode chamber, 120 mL of 500 mM Na2SO4 solution was added to the two desalination chambers, and the desalination chambers were connected through external pipes for brine circulation. 120 mL of 6 mM (NH4)2SO4 solution was added to the anode chamber, and the above 120 mL of actual urine after hydrolysis was added to the cathode chamber. The system was powered by a pulse power supply (SOYI-1506M), a series circuit was used between the 6 chambers of the reactor, and the system adopted a constant pressure operation mode. The reaction time was set to 12 h, and sampling was carried out every 2 h. The pH of each chamber was measured and recorded, and 1 mL was sampled each time and stored in a centrifuge tube. The above experiments were all carried out at an ambient temperature of 25±1°C.

[0089] Figure 7 This diagram shows a strategy for improving the efficiency of ammonia nitrogen recovery from simulated urine using a transmembrane pulse electrochemical system. The duty cycles for reaction times 0-2 hours, 2-4 hours, 4-6 hours, 6-8 hours, and 8-10 hours were set to 63%, 50%, 44%, 38%, and 25%, respectively. The duty cycle under direct current conditions was set to 100% for reaction times 0-10 hours. Figure 8 The figure below compares the ammonia nitrogen removal and recovery efficiency under direct current conditions and the boost strategy. After 10 hours of operation, the ammonia removal efficiency under direct current conditions and the boost strategy were 91.8% and 77.0%, respectively, and the ammonia recovery efficiency was 74.0% and 65.2%, respectively. Figure 9 This figure compares the specific energy consumption of ammonia nitrogen recovery under DC conditions and the boost strategy. After 10 hours of operation, the specific energy consumption under the boost strategy (19.5 kWh / kg N) decreased by 76.9% compared to the specific energy consumption under DC conditions (84.4 kWh / kg N). In summary, the transmembrane pulse electrochemical system offers significant energy savings compared to DC power sources for recovering ammonia from actual urine. The BPNN-based ammonia nitrogen recovery efficiency prediction model can improve the efficiency of transmembrane pulse electrochemical recovery of wastewater ammonia and has promising application prospects.

[0090] It can be seen that the present invention achieves at least the following technical effects:

[0091] The present invention aims to reduce the energy consumption of electrochemical recovery of ammonia nitrogen from sewage. Combining the low energy consumption characteristics of pulse power supply, the pulse power supply is combined with a transmembrane electrochemical system to explore the feasibility of reducing energy consumption in the ammonia recovery process under pulse conditions. Furthermore, based on the good learning and prediction functions of BPNN for complex parameter experiments, this study proposes an operating strategy for improving the efficiency of the transmembrane pulse electrochemical recovery system for ammonia nitrogen from sewage. Finally, the strategy was verified and evaluated by treating actual human urine. In short, the present invention aims to provide a high-efficiency, no-additive-required, easy-to-scale, and low-energy-cost electrochemical recovery solution for ammonia nitrogen from actual sewage, in order to provide technical support for the recycling of ammonia nitrogen resources and the protection of the ecology.

[0092] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0093] The above is an introduction to a method embodiment. The following further illustrates the solution of the present invention through an apparatus embodiment.

[0094] Figure 10A structural diagram of a device for recovering ammonia nitrogen from wastewater by transmembrane pulse electrochemistry based on machine learning provided in an embodiment of the present invention, such as Figure 10 As shown, the apparatus 1000 may include:

[0095] The acquisition module 1010 is used to obtain the pulse frequency, applied voltage, cathode liquid initial concentration, anode liquid initial concentration, and brine initial concentration required for recovering ammonia nitrogen from target wastewater using a transmembrane pulse electrochemical system.

[0096] The receiving module 1020 is used to receive multiple different pulse duty cycle configuration information for the target sewage input by the user, wherein one pulse duty cycle configuration information is used to characterize the pulse duty cycle configured in each time period during the ammonia nitrogen recovery of the target sewage using the transmembrane pulse electrochemical system.

[0097] The prediction module 1030 is used to input any pulse duty cycle configuration information together with the pulse frequency, external voltage, cathode liquid initial concentration, anode liquid initial concentration, and brine initial concentration into a pre-trained ammonia nitrogen recovery efficiency prediction model to obtain the ammonia nitrogen recovery efficiency information corresponding to the pulse duty cycle configuration information, wherein the ammonia nitrogen recovery efficiency includes ammonia nitrogen removal efficiency, ammonia nitrogen recovery efficiency, and ammonia nitrogen recovery specific energy consumption.

[0098] The selection module 1040 is used to select, based on the ammonia nitrogen recovery efficiency information corresponding to the multiple pulse duty cycle configuration information, the pulse duty cycle configuration information with the ammonia nitrogen removal efficiency and the ammonia nitrogen recovery efficiency being not less than the corresponding preset thresholds and the minimum ammonia nitrogen recovery energy consumption from the multiple pulse duty cycle configuration information.

[0099] The recovery module 1050 is used to recover ammonia nitrogen from the target wastewater using a transmembrane pulse electrochemical system based on the selected pulse duty cycle configuration information and pulse frequency, applied voltage, initial cathode liquid concentration, initial anode liquid concentration, and initial brine concentration.

[0100] It is understandable that Figure 10 The various modules / units in the device 1000 shown have the function of implementing Figure 1 The functions of the various steps in the method 100 shown and their ability to achieve corresponding technical effects are not described here for the sake of brevity.

[0101] Figure 111 is a block diagram of an exemplary electronic device capable of implementing embodiments of the present invention. Electronic device 1100 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 1100 may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0102] like Figure 11 As shown, the electronic device 1100 may include a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 1103. Various programs and data required for the operation of the electronic device 1100 may also be stored in the RAM 1103. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0103] Multiple components in the electronic device 1100 are connected to the I / O interface 1105, including an input unit 1106, such as a keyboard, a mouse, etc.; an output unit 1107, such as various types of displays, speakers, etc.; a storage unit 1108, such as a magnetic disk, an optical disk, etc.; and a communication unit 1109, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1109 allows the electronic device 1100 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0104] The computing unit 1101 may be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 1101 performs the various methods and processes described above, such as method 100. For example, in some embodiments, method 100 may be implemented as a computer program product, including a computer program tangibly embodied in a computer-readable medium, such as a storage unit 1108. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 1100 via the ROM 1102 and / or the communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, one or more steps of the method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to execute the method 100 in any other appropriate manner (eg, by means of firmware).

[0105] The various embodiments described above in the present invention can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0106] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0107] In the context of the present invention, computer-readable media can be tangible media that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable media can be a computer-readable signal medium or a computer-readable storage medium. Computer-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. More specific examples of computer-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0108] It should be noted that the present invention also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute method 100 and achieve the corresponding technical effect achieved by executing the method in an embodiment of the present invention. For the sake of brevity, they will not be repeated here.

[0109] In addition, the present invention also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method 100 is implemented.

[0110] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in the present invention can be achieved. The present invention is not limited here.

[0111] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for recovering ammonia nitrogen from sewage by transmembrane pulse electrochemistry based on machine learning, characterized in that: The method comprises: Obtain the pulse frequency, applied voltage, catholyte initial concentration, anolyte initial concentration, and brine initial concentration required for ammonia nitrogen recovery from target wastewater using a transmembrane pulse electrochemical system; Receive multiple different pulse duty cycle configuration information for target sewage input by the user, wherein one pulse duty cycle configuration information is used to represent the pulse duty cycle configured in each time period during the ammonia nitrogen recovery of the target sewage using the transmembrane pulse electrochemical system; For any pulse duty cycle configuration information, input it, along with the pulse frequency, applied voltage, initial cathode liquid concentration, initial anolyte concentration, and initial brine concentration, into a pre-trained ammonia nitrogen recovery efficiency prediction model to obtain the ammonia nitrogen recovery efficiency information corresponding to the pulse duty cycle configuration information. The ammonia nitrogen recovery efficiency includes ammonia nitrogen removal efficiency, ammonia nitrogen recovery efficiency, and ammonia nitrogen recovery specific energy consumption. Based on the ammonia nitrogen recovery efficiency information corresponding to the multiple pulse duty cycle configuration information, select the pulse duty cycle configuration information with the ammonia nitrogen removal efficiency and the ammonia nitrogen recovery efficiency not less than the corresponding preset thresholds and the minimum ammonia nitrogen recovery specific energy consumption from the multiple pulse duty cycle configuration information; Based on the selected pulse duty cycle configuration information as well as the pulse frequency, applied voltage, initial cathode liquid concentration, initial anode liquid concentration, and initial brine concentration, a transmembrane pulse electrochemical system is used to recover ammonia nitrogen from the target wastewater.

2. The method according to claim 1, characterized in that The output voltage of the pulse power supply in the transmembrane pulse electrochemical system is 0-1000V, the output current is 0-9000A, the output power is 0-9000KVA, the frequency range is 0.1-50000HZ, and the duty cycle range is 0-100%.

3. The method according to claim 1, characterized in that The chambers in the transmembrane pulse electrochemical system include a cathode chamber, an anode chamber, two desalination chambers, a secondary cathode chamber and a secondary anode chamber; The auxiliary cathode chamber is connected to its corresponding desalination chamber by a cation exchange membrane, the auxiliary anode chamber is connected to its corresponding desalination chamber by an anion exchange membrane, and the cathode chamber and the anode chamber are connected by a gas-permeable and hydrophobic membrane; The auxiliary anode is an iridium-tantalum-titanium anode, and the auxiliary cathode is a stainless steel wire mesh.

4. The method according to claim 1, wherein The ammonia nitrogen recovery efficiency prediction model is trained by the following steps: Acquire data from ammonia nitrogen recovery experiments using a transmembrane pulse electrochemical system and construct a dataset based on this data; The sample data in the dataset include: pulse duty cycle configured in each time period during the ammonia nitrogen recovery experiment, pulse frequency, applied voltage, initial cathode liquid concentration, initial anode liquid concentration, initial brine concentration, cathode liquid concentration, and anode liquid concentration; the label data in the dataset include: ammonia nitrogen removal efficiency, ammonia nitrogen recovery efficiency, and ammonia nitrogen recovery specific energy consumption during the ammonia nitrogen recovery experiment; The initial neural network was trained according to the data set to obtain an ammonia nitrogen recovery efficiency prediction model.

5. The method according to claim 4, characterized in that The initial neural network is trained according to the data set to obtain an ammonia nitrogen recovery efficiency prediction model, including: Normalize the data in the dataset and divide the normalized dataset into a training set and a test set; The initial neural network is trained using the training set, and at the end of the training, the performance of the current neural network is tested using the test set. If the performance test is passed, the current neural network is used as an ammonia nitrogen recovery efficiency prediction model.

6. The method according to claim 5, characterized in that Use the training set to train the initial neural network, including: Input the sample data in the training set into the initial neural network to obtain the output result, calculate the error between the output result and the label data, update the model parameters of the neural network according to the error, and continuously iterate and update until the preset stopping condition is met.

7. The method according to claim 6, characterized in that The neural network is a back propagation neural network BPNN.

8. A transmembrane pulse electrochemical device for recovering ammonia nitrogen from wastewater based on machine learning, characterized in that: The device comprises: An acquisition module is used to obtain the pulse frequency, applied voltage, catholyte initial concentration, anolyte initial concentration, and brine initial concentration required for recovering ammonia nitrogen from target wastewater using a transmembrane pulse electrochemical system; A receiving module is used to receive multiple different pulse duty cycle configuration information for target sewage input by a user, wherein one pulse duty cycle configuration information is used to represent the pulse duty cycle configured in each time period during the ammonia nitrogen recovery of the target sewage using the transmembrane pulse electrochemical system; A prediction module is used to input any pulse duty cycle configuration information, along with the pulse frequency, applied voltage, cathode liquid initial concentration, anolyte initial concentration, and brine initial concentration, into a pre-trained ammonia nitrogen recovery efficiency prediction model to obtain ammonia nitrogen recovery efficiency information corresponding to the pulse duty cycle configuration information, wherein the ammonia nitrogen recovery efficiency includes ammonia nitrogen removal efficiency, ammonia nitrogen recovery efficiency, and ammonia nitrogen recovery specific energy consumption; A selection module is used to select, based on the ammonia nitrogen recovery efficiency information corresponding to the multiple pulse duty cycle configuration information, the pulse duty cycle configuration information with the ammonia nitrogen removal efficiency and the ammonia nitrogen recovery efficiency being not less than the corresponding preset thresholds and the minimum ammonia nitrogen recovery specific energy consumption from the multiple pulse duty cycle configuration information; The recovery module is used to recover ammonia nitrogen from the target wastewater using a transmembrane pulse electrochemical system based on the selected pulse duty cycle configuration information and pulse frequency, applied voltage, initial cathode liquid concentration, initial anode liquid concentration, and initial brine concentration.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Method for eliminating oxynitride from air flow and the special equipment thereof

    CN101032678A

  • Osmotic bioelectrochemical systems

    WO2013009797A1