A method and system for membrane fouling control based on deep learning

Abstract

The present disclosure relates to a deep learning-based membrane fouling control method and system, which acquires real-time operation parameters of a membrane system and flocculation visual images of an electrocoagulation system by coupling the electrocoagulation and the membrane system, and calculates a membrane fouling index accordingly. Meanwhile, a deep learning image recognition model is used to extract flocculation features. The membrane fouling index and the flocculation features are fused and input into a control decision model to generate a control instruction, so as to dynamically adjust the operation parameters of the electrocoagulation, maintain the membrane fouling index at a set threshold, and achieve precise and efficient membrane fouling control.

Description

Technical Field

[0001] This disclosure relates to the field of wastewater treatment technology, and in particular to a membrane fouling control method and system based on deep learning. Background Technology

[0002] Membrane fouling is a common problem in membrane filtration. Existing membrane fouling treatment technologies, particularly traditional physical and chemical methods, involve large amounts of reagents, cumbersome operation and management, and cannot accurately determine reagent dosage based on the actual water environment and water treatment needs to reduce membrane wear. This results in low efficiency in controlling membrane fouling, leading to high operating costs and short membrane lifespan, severely restricting the application of membrane systems in water purification and treatment, and failing to effectively improve membrane lifespan and thus control operating costs. Summary of the Invention

[0003] To address the aforementioned technical problems, this disclosure provides a membrane fouling control method and system based on deep learning.

[0004] According to one aspect of the present invention, a deep learning-based membrane fouling control method is provided, comprising the following steps: The system acquires real-time operating parameters of the membrane system and visual images of the electrocoagulation system; the electrocoagulation system performs electrochemical flocculation treatment, and the membrane system is used to filter and separate the materials processed by the electrocoagulation system. Based on the real-time operating parameters, the membrane fouling index is obtained; Flocculation features are obtained by processing the flocculation visual image using a deep learning image recognition model; Based on the membrane fouling index and the flocculation characteristics, control commands are obtained using a pre-trained control decision model. According to the control command, the operating parameters of the electrocoagulation system are adjusted so that the membrane fouling index reaches the set threshold.

[0005] According to another aspect of the present invention, a deep learning-based membrane fouling control system is provided, comprising: Electrocoagulation system, used for electrochemical flocculation treatment; A membrane system, connected to the outlet of the electrocoagulation system, is used to filter and separate the materials to be treated by the electrocoagulation system. Control system, including: The data acquisition module is used to acquire real-time operating parameters of the membrane system and visual images of the electrocoagulation system. The membrane fouling assessment module is used to obtain the membrane fouling index based on the real-time operating parameters. The flocculation feature acquisition module is used to acquire flocculation features by processing the flocculation visual image through a deep learning image recognition model. The control decision module is used to obtain control instructions for adjusting the operating parameters of the electrocoagulation system based on the membrane fouling index and the flocculation characteristics using a pre-trained control decision system; and to adjust the operating parameters of the electrocoagulation system according to the control instructions so that the membrane fouling index reaches a set threshold.

[0006] The technical solution provided in this disclosure has the following advantages compared with the prior art: This invention achieves precise control of membrane fouling by real-time monitoring of the operating data of the membrane system and electrocoagulation system, combined with a pre-trained deep learning model. It dynamically adjusts electrocoagulation operating parameters based on the fouling status. The invention utilizes image recognition technology to identify the floc state in electrocoagulation, enabling more intuitive and accurate acquisition of floc density, particle size, and distribution characteristics, providing a more reliable basis for control decisions. By using operating parameters and floc images, a membrane fouling index is obtained to evaluate the membrane system. Controlling electrocoagulation operating parameters based on this index effectively reduces reagent consumption, improves operating efficiency, and lowers operating costs. This achieves the goal of effectively controlling membrane fouling, controlling reagent dosage, extending membrane lifespan, reducing membrane replacement frequency, and lowering maintenance costs. Attached Figure Description

[0007] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0008] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0009] Figure 1 This is a schematic flowchart of the deep learning-based membrane fouling control method described in the embodiments of this disclosure; Figure 2 This is a schematic diagram of the framework structure of the membrane fouling control system described in an embodiment of this disclosure; Figure 3 This is a schematic diagram of the framework of the control system described in the embodiments of this disclosure; Figure 4 This is a schematic diagram of the framework of the electronic device described in the embodiments of this disclosure; Figure 5 This is a schematic diagram of the framework of the deep learning-based membrane fouling control system described in the embodiments of this disclosure; Figure 6 This is a schematic flowchart of another control system according to an embodiment of the present disclosure; Figure 7 This is a schematic flowchart of another control system according to an embodiment of the present disclosure. Detailed Implementation

[0010] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0011] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0012] The embodiments of this application provide a membrane fouling control method based on deep learning, referring to... Figure 1 , Figure 5 and Figure 6 The method will be described in detail, including: Step S1: Obtain the real-time operating parameters of the membrane system and the flocculation visual images of the electrocoagulation system.

[0013] The electrocoagulation system performs electrochemical flocculation treatment, while the membrane system is used to filter and separate the materials processed by the electrocoagulation system.

[0014] In this embodiment, after the membrane fouling control system using the method of this application is started, the raw water to be treated is first sent to the electrocoagulation system for flocculation treatment to obtain pre-treated water. This system uses metals such as aluminum or iron as electrodes, and discharges by applying voltage to generate Al. 3+ or Fe 3+ Metal cations are used as flocculants. These ions achieve flocculation through compression of the colloidal double layer and adsorption bridging, while the generated hydrogen bubbles accelerate the floating and separation of pollutants. It also possesses multiple functions such as sterilization, decolorization, and deodorization. It is particularly suitable for treating complex industrial wastewater.

[0015] In this process, visual images of flocculation are acquired by multiple high-resolution visual recognition cameras installed in the reactor sight glass or specific observation area of ​​the electrocoagulation system. The images of the flocs in the reactor, i.e., the visual images of the flocs, are acquired in real time and continuously.

[0016] Water pretreated by electrocoagulation enters the membrane system for precise filtration and separation. This membrane system is equipped with multiple high-precision flow and pressure sensors. These sensors, strategically placed within the system, collect real-time operational data and provide feedback on the operating status of the filtration membranes.

[0017] In some embodiments, see Figure 6 The real-time operating parameters of these membrane systems specifically include transmembrane pressure differential. TMP Inlet water pressure P Product flow rate q and cross-flow ratio r These data serve as a direct basis for assessing membrane fouling.

[0018] Step S2: Obtain the membrane fouling index based on real-time operating parameters.

[0019] In some embodiments, the real-time operating parameters collected in step S1, such as transmembrane pressure difference, are used. TMP Inlet water pressure P Water production flow rate q and cross-flow ratio r， By performing analysis and processing, the designed membrane fouling function can be used to process the operating parameters.

[0020] In this embodiment, see Figure 6 Using the membrane fouling function to measure the transmembrane pressure difference TMP Inlet water pressure P Water production flow rate q and cross-flow ratio r Perform calculations ， A quantified membrane fouling index is obtained. This membrane fouling function is derived by comparing the operating parameters of the membrane system under initial and current operating conditions, and its formula is as follows:

[0021] in, FI The membrane fouling index, TCF This is the temperature correction factor for the membrane system. TCF 0 represents the temperature correction factor during the initial operation of the membrane system; q For real-time water production flow rate, q 0 represents the initial product water flow rate; T MP For real-time transmembrane pressure difference, TMP 0 represents the initial transmembrane pressure difference; P For real-time inlet water pressure, P 0 represents the initial inlet pressure. r For real-time cross-flow ratio, r 0 represents the initial cross-flow ratio. The cross-flow ratio is the ratio of the influent flow rate to the permeate flow rate. As can be seen from the operation of the membrane system, r≥1, and the larger the value of r, the lower the operating efficiency of the membrane system.

[0022] The obtained membrane fouling index FI The value can accurately and quantitatively reflect the current degree of fouling in a membrane system. This is achieved through the membrane fouling index. FI The value is used to determine the operating status of the membrane system and further predict the types and intensity of potential membrane fouling, such as colloidal fouling, organic fouling, or microbial fouling. Membrane Fouling Index FI The higher the value, the more severe the membrane fouling, the more significant the decrease in membrane flux, and the lower the operating efficiency of the membrane fouling control system.

[0023] Step S3: Obtain flocculation features by processing the flocculation visual image using a deep learning image recognition model.

[0024] The flocculation visual image acquired in step S1 is input into a deep learning image recognition model. In this embodiment, the model uses the YOLOv8 deep learning algorithm based on image recognition. This algorithm, through its free anchor frame design and decoupling of the detection head, can directly and quickly predict flocs in the image. In this embodiment, the flocculation feature is the image feature of alum flocs; that is, in this embodiment, the deep learning image recognition model can quickly and effectively identify the location and type of alum flocs.

[0025] The deep learning image recognition model in this embodiment is trained to minimize the loss function, thereby accurately identifying key features such as the size, density, and distribution of flocculants. Specifically, the image recognition process first uses YOLOv8 to extract image features through a backbone network, then uses a neck network for multi-scale feature fusion, and finally outputs the detection results through a detection head. See also... Figure 6 In this embodiment, by accurately defining the bounding box around the floc, the floc particle size φ, floc density ρ, and distribution quantity m are obtained, facilitating further quantitative analysis. Finally, a set of quantified flocculation characteristic data is output, including floc density ρ, floc particle size φ, and distribution quantity m.

[0026] These characteristics intuitively reflect the real-time effect of electrocoagulation, providing a reliable and intuitive basis for subsequent control decisions.

[0027] Step S4: Based on the membrane fouling index and flocculation characteristics, obtain control commands using a pre-trained control decision model.

[0028] The membrane fouling index FI obtained in step S2 is fused with the flocculation characteristics obtained in step S3 to form a comprehensive, multi-dimensional system state input vector.

[0029] The integrated input vector is then fed into a pre-trained control decision model. This model, through learning from massive amounts of historical operational data, has mastered the optimal electrocoagulation operating parameter strategy to be adopted under different combinations of membrane fouling levels and flocculation effects.

[0030] In some embodiments, after obtaining the flocculation characteristics, the method further includes: Based on historical operating data of the membrane system and historical flocculation visual images of the electrocoagulation system, a deep neural network model is trained to obtain a trained control decision model.

[0031] In this embodiment, the training process of the deep neural network model is as follows: First, a large dataset is constructed based on historical operating data of the membrane system and historical flocculation visual images of the electrocoagulation system.

[0032] Then, the dataset is used to train the deep neural network model. The training process includes forward propagation, where the deep neural network model predicts the input data based on the current parameters, calculates the difference between the model's prediction and the actual results, calculates the gradient backpropagation of the deep neural network model parameters based on the loss function, and updates the parameters. In this embodiment, gradient descent is used to adjust the deep neural network model parameters to reduce the loss.

[0033] During the operation of the membrane fouling control system, a large amount of real-time operational data is used to continuously adjust parameters and iteratively feed back through a backpropagation algorithm, in order to achieve a lower membrane fouling index (FI) target for optimized system control. The optimization objective of this model is to bring the membrane fouling index to a set threshold.

[0034] In this embodiment, the control decision model analyzes and judges the real-time input status and outputs a set of precise control commands. These commands directly correspond to the operating parameters of the electrocoagulation system that need to be adjusted.

[0035] Step S5: Adjust the operating parameters of the electrocoagulation system according to the control command so that the membrane fouling index reaches the set threshold.

[0036] The control command generated in step S4 is sent to the electrocoagulation system to adjust the current intensity and processing flow rate of the electrocoagulation system, and the immersion volume V is changed by adjusting the electrode spacing of the electrolytic cell of the electrocoagulation system, thereby matching a suitable electrocoagulation intensity.

[0037] After adjustment, the flocculation effect produced by electrocoagulation will change, thus affecting the water quality entering the membrane system. The operating parameters of the membrane system will also change accordingly, leading to new membrane fouling. FIThe index is recalculated. Steps S1 to S5 are repeated continuously, forming an iterative control loop. Through this iterative feedback mechanism, continuous optimization is achieved, driving the membrane fouling index FI to gradually decrease and stabilize within the set threshold range, ultimately achieving a lower membrane fouling index and more stable operation.

[0038] In some embodiments, the electrocoagulation system uses electrocoagulation intensity to characterize the electrocoagulation result; The determination of electrocoagulation strength includes:

[0039] in, S EF This represents the electrocoagulation intensity, used to provide feedback on the intensity of electrocoagulation. The electrocoagulation intensity coefficient; m This represents the theoretical mass of dissolved anode metal in the electrocoagulation system. I t is the applied current; Q is the water flow rate of the electrocoagulation system; V is the immersion volume of water flowing through part of the electrolytic cell in the electrocoagulation system; M is the molar mass of the anode metal in the electrocoagulation system; z is the valence electron number of the metal ion; and F is the Faraday constant, 96485 C / mol. In some embodiments, a deep learning-based membrane fouling control system is also provided, see [link / reference]. Figure 2 , Figure 3 , Figure 6 and Figure 7 Specifically, it includes: Electrocoagulation system 100 is used for electrochemical flocculation treatment.

[0040] Specifically, the system can use a fusible metal such as iron or aluminum as the anode, and generate Al in situ by applying voltage to discharge. 3+ or Fe 3+ The system uses metal cationic flocculants. These ions achieve efficient flocculation through compression of the colloidal double layer and adsorption bridging, while the hydrogen microbubbles generated by electrolysis accelerate the flotation and separation of pollutants. It also possesses multiple functions such as sterilization, decolorization, and deodorization, making it particularly suitable for treating complex industrial wastewater. In some embodiments, the system is equipped with an electrolytic cell with automatically adjustable electrode spacing, allowing the control system 300 to precisely control the immersion volume V of the electrolytic cell. Furthermore, the system is equipped with a current meter for real-time monitoring and automatic adjustment by the control system to precisely control the intensity of electrocoagulation.

[0041] Membrane system 200, connected to the effluent end of the electrocoagulation system, is used to filter and separate the waste materials from the electrocoagulation system. As the core unit of water treatment, this membrane system is equipped with multiple high-precision flow and pressure sensors. These sensors can collect real-time operating data of the membrane system, such as transmembrane pressure differential. TMP Water production flow rate q and cross-flow ratio r These key operating parameters provide direct data for the control system to assess membrane fouling.

[0042] The control system 300 is used to receive and analyze data and issue control commands, and specifically includes the following functional modules: Data acquisition module 310 is used to acquire real-time operating parameters of the membrane system and visual images of the electrocoagulation system; this module acquires transmembrane pressure difference from sensors in membrane system 200. TMP Water production flow rate q and cross-flow ratio r On the one hand, data such as flocs are collected in real time and continuously through multiple visual recognition cameras installed on the electrocoagulation reactor, and on the other hand, the visual image stream of flocs, i.e., alum flocs, is collected in the reactor.

[0043] The membrane fouling assessment module 320 is used to obtain the membrane fouling index based on real-time operating parameters. This module receives operating parameters from the data acquisition module 310 and calculates using a preset membrane fouling index to obtain a membrane fouling index that accurately and quantitatively reflects the current degree of fouling in the membrane system. FI Indices. Membrane fouling index. FI The higher the value, the more severe the membrane fouling and the more significant the decrease in flux.

[0044] The flocculation feature acquisition module 330 is used to acquire flocculation features by processing the flocculation visual image using a deep learning image recognition model. This module inputs the visual image acquired by the data acquisition module 310 into an advanced deep learning image recognition model; in this embodiment, YOLOv8 is used. Through YOLOv8 model analysis, key features of the flocs can be accurately identified and quantified, such as floc density ρ, floc size φ, and distribution quantity m. These features intuitively reflect the real-time effect of electrocoagulation.

[0045] The control decision module 340 is used to acquire control commands for adjusting the operating parameters of the electrocoagulation system based on the membrane fouling index and flocculation characteristics using a pre-trained control decision system; and to adjust the operating parameters of the electrocoagulation system according to the control commands so that the membrane fouling index reaches a set threshold. This module first processes the membrane fouling index output by the membrane fouling assessment module 320. FI The flocculation features output by the flocculation feature acquisition module 330 are fused to form a comprehensive system state vector. This vector is then input into a pre-trained control decision model, which has learned the optimal control strategy under different pollution conditions by studying massive amounts of historical data. Finally, the module outputs a set of precise control commands and adjusts the operating parameters of the electroflocculation system 100 according to these commands.

[0046] For example, it automatically adjusts its current intensity and processing flow rate, and changes the immersion volume V by adjusting the electrode spacing of the electrolyzer, thereby matching a suitable electrocoagulation intensity. Through this dynamic adjustment, the membrane fouling index FI is driven to gradually decrease and stabilize within the set threshold range, ultimately achieving a lower membrane fouling index and more stable system operation.

[0047] See Figure 7 In some embodiments, a membrane fouling control system based on deep learning is also provided, and the system is constructed accordingly. This system comprises both hardware and software components; the hardware conforms to… Figure 6 The flowchart is based on the following parts: raw water supply, electrocoagulation system 100, membrane system and deep learning membrane fouling control system 300; the software that applies the control method is the deep learning membrane fouling control system.

[0048] The raw water supply section supplies water to the entire system and can automatically adjust the inlet flow rate under the control of a deep learning-based control system.

[0049] The electrocoagulation system 100 can use an electrolytic cell with iron or aluminum electrodes and an automatically adjustable electrode spacing, which is used by the control system 300 to automatically adjust the immersion volume of the electrolytic cell. The electrocoagulation system 100 is equipped with multiple visual recognition cameras, which, together with the image recognition deep learning algorithm model, can automatically identify the state of the flocs produced by electrocoagulation. The electrocoagulation system 100 is equipped with a current intensity meter, which can automatically adjust the electrocoagulation intensity of the electrocoagulation system, and can be automatically controlled and adjusted by the control system.

[0050] The membrane system 200 is the core treatment component of the water treatment system. This system is equipped with multiple flow and pressure sensors, which can be controlled by the control system 300 to provide real-time feedback on the operating status of the system 200, such as transmembrane pressure difference permeate flow rate, cross-flow ratio, and other operating parameters.

[0051] The deep learning-based control system 300 can accept, analyze, and store real-time data from other units, and use its deep learning-based control method to intelligently control the entire system.

[0052] Embodiments of this application also provide an electronic device, with reference to Figure 4 It includes a memory 601 and a processor 602, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above-described server component identification method embodiments.

[0053] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the server component identification method embodiments described above when running.

[0054] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0055] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A membrane fouling control method based on deep learning, characterized in that, include: Acquire real-time operating parameters of the membrane system and visual images of the electrocoagulation system; The electrocoagulation system performs electrochemical flocculation treatment, and the membrane system is used to filter and separate the processed material from the electrocoagulation system. Based on the real-time operating parameters, the membrane fouling index is obtained; Flocculation features are obtained by processing the flocculation visual image using a deep learning image recognition model; Based on the membrane fouling index and the flocculation characteristics, control commands are obtained using a pre-trained control decision model. According to the control command, the operating parameters of the electrocoagulation system are adjusted so that the membrane fouling index reaches the set threshold. The real-time operating parameters include transmembrane pressure difference, permeate flow rate, and cross-flow ratio; Based on the transmembrane pressure difference, permeate flow rate, and cross-flow ratio, the membrane fouling index is obtained; The acquisition of the membrane fouling index includes: in, FI The membrane fouling index, TCF This is the temperature correction factor for the membrane system. TCF 0 represents the temperature correction factor during the initial operation of the membrane system; q For real-time water production flow rate, q 0 represents the initial product water flow rate; T MP For real-time transmembrane pressure difference, TMP 0 represents the initial transmembrane pressure difference; P For real-time inlet water pressure, P 0 represents the initial inlet pressure. r For real-time cross-flow ratio, r 0 represents the initial crossflow ratio; The electrocoagulation system uses electrocoagulation intensity to characterize the electrocoagulation result; The acquisition of the electrocoagulation strength includes: in, S EF This represents the electrocoagulation intensity, used to provide feedback on the intensity of electrocoagulation. The electrocoagulation intensity coefficient; m This represents the theoretical mass of dissolved anode metal in the electrocoagulation system. I The applied current; t Let be the electrolysis time, Q be the water flow rate of the electrocoagulation system, V be the immersion volume of the part of the electrolytic cell through which water flows in the electrocoagulation system, M be the molar mass of the anode metal in the electrocoagulation system, z be the number of valence electrons of the metal ion, and F be the Faraday constant.

2. The membrane fouling control method based on deep learning according to claim 1, characterized in that, The flocculation characteristics include the density, particle size, and distribution of the flocs.

3. The membrane fouling control method based on deep learning according to claim 1, characterized in that, After obtaining the flocculation characteristics, the method further includes: Based on historical operating data of the membrane system and historical flocculation visual images of the electrocoagulation system, a deep neural network model is trained to obtain a trained control decision model. The optimization objective of the control decision model is to bring the membrane fouling index to a set threshold.

4. The membrane fouling control method based on deep learning according to claim 1, characterized in that, The operating parameters of the electrocoagulation system include current intensity, processing flow rate, and immersion volume; The operating parameters of the electrocoagulation system include at least one.

5. A membrane fouling control system based on deep learning, applied to the method described in any one of claims 1 to 4, characterized in that, include: Electrocoagulation system, used for electrochemical flocculation treatment; A membrane system, connected to the outlet of the electrocoagulation system, is used to filter and separate the materials to be treated by the electrocoagulation system. Control system, including: The data acquisition module is used to acquire real-time operating parameters of the membrane system and visual images of the electrocoagulation system. The membrane fouling assessment module is used to obtain the membrane fouling index based on the real-time operating parameters. The flocculation feature acquisition module is used to acquire flocculation features by processing the flocculation visual image through a deep learning image recognition model. The control decision module is used to obtain control instructions for adjusting the operating parameters of the electrocoagulation system based on the membrane fouling index and the flocculation characteristics using a pre-trained control decision system; and to adjust the operating parameters of the electrocoagulation system according to the control instructions so that the membrane fouling index reaches a set threshold. The real-time operating parameters include transmembrane pressure difference, permeate flow rate, and cross-flow ratio; Based on the transmembrane pressure difference, permeate flow rate, and cross-flow ratio, the membrane fouling index is obtained; The acquisition of the membrane fouling index includes: in, FI The membrane fouling index, TCF This is the temperature correction factor for the membrane system. TCF 0 represents the temperature correction factor during the initial operation of the membrane system; q For real-time water production flow rate, q 0 represents the initial product water flow rate; T MP For real-time transmembrane pressure difference, TMP 0 represents the initial transmembrane pressure difference; P For real-time inlet water pressure, P 0 represents the initial inlet pressure. r For real-time cross-flow ratio, r 0 represents the initial crossflow ratio; The electrocoagulation system uses electrocoagulation intensity to characterize the electrocoagulation result; The acquisition of the electrocoagulation strength includes: in, S EF This represents the electrocoagulation intensity, used to provide feedback on the intensity of electrocoagulation. The electrocoagulation intensity coefficient; m This represents the theoretical mass of dissolved anode metal in the electrocoagulation system. I The applied current; t Let be the electrolysis time, Q be the water flow rate of the electrocoagulation system, V be the immersion volume of the part of the electrolytic cell through which water flows in the electrocoagulation system, M be the molar mass of the anode metal in the electrocoagulation system, z be the number of valence electrons of the metal ion, and F be the Faraday constant.

6. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the deep learning-based membrane fouling control method as described in any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, it implements the steps of the deep learning-based membrane fouling control as described in any one of claims 1 to 4.

Images