Membrane pollution prediction method and device based on extracellular polymeric substance data driving

Abstract

The embodiment of the invention provides a membrane pollution prediction method and device based on extracellular polymeric substance data driving, and relates to the technical field of sewage treatment. The method comprises the following steps: acquiring EPS (Expandable Polystyrene) characteristic data and a membrane pollution rate in an operation process of the anaerobic membrane bioreactor; the method comprises the following steps: by taking EPS characteristic data in an operation process of an anaerobic membrane bioreactor as samples and taking a membrane pollution rate in the operation process of the anaerobic membrane bioreactor as labels corresponding to the samples, constructing a data set according to a plurality of samples and the labels corresponding to the samples; the random forest model is trained by using the data set to obtain the membrane pollution prediction model with the optimal prediction capability, so that the membrane pollution rate of the anaerobic membrane bioreactor is rapidly and accurately predicted based on the model, and the membrane pollution prediction effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment, and in particular to a membrane pollution prediction method and device based on extracellular polymer data drive. Background Art

[0002] Anaerobic membrane bioreactors (AnMBRs) combine membrane filtration technology with anaerobic fermentation technology to overcome the limitations of traditional anaerobic digestion processes. Although the membrane filtration process helps to increase the value of anaerobic functional microorganisms and improve the quality of effluent, the membrane fouling problem caused by this restricts the further promotion and application of AnMBRs. Extracellular polymers (EPS) are complex high molecular polymers that usually account for 60-80% of the total organic matter in the digestate. EPS has high filtration resistance and strong adhesion ability, and is easy to form a gel layer with highly cross-linked and polymer entanglement characteristics on the membrane surface, aggravating membrane fouling.

[0003] The physicochemical properties of different EPS layers have obvious nonlinear effects on membrane fouling in AnMBRs. Traditional mathematical models or "black box" models may not be able to fully capture these complex relationships and effectively predict the progress of membrane fouling. Therefore, how to effectively analyze the nonlinear relationship between EPS and membrane fouling and efficiently predict the progress of membrane fouling has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In a first aspect, an embodiment of the present invention provides a membrane fouling prediction model training method based on extracellular polymer data-driven, the method comprising:

[0005] Obtain EPS characteristic data and membrane fouling rate during the operation of anaerobic membrane bioreactor;

[0006] Taking the EPS characteristic data during the operation of the anaerobic membrane bioreactor as samples, and the membrane fouling rate during the operation of the anaerobic membrane bioreactor as the label corresponding to the sample, a data set is constructed based on multiple samples and their corresponding labels;

[0007] The random forest model was trained using the data set to obtain a membrane fouling prediction model.

[0008] In some implementations of the first aspect, obtaining characteristic data of extracellular polymers (EPS) and membrane fouling rate during the operation of an anaerobic membrane bioreactor includes:

[0009] The digestate during the operation of the anaerobic membrane bioreactor was tested to obtain EPS characteristic data;

[0010] The membrane components in the anaerobic membrane bioreactor are monitored during operation to obtain the membrane fouling rate.

[0011] In some implementable methods of the first aspect, the EPS characteristic data include: protein concentration of soluble EPS, polysaccharide concentration of soluble EPS, protein concentration of loosely bound EPS, polysaccharide concentration of loosely bound EPS, protein concentration of tightly bound EPS, polysaccharide concentration of tightly bound EPS; the membrane fouling rate includes: transmembrane pressure difference growth rate.

[0012] In some implementations of the first aspect, a random forest model is trained using a data set to obtain a membrane fouling prediction model, including:

[0013] Divide the data set into training set and test set according to the preset ratio;

[0014] Use the training set to train the random forest model, and use the test set to evaluate the performance of the trained random forest model;

[0015] If the trained random forest model passes the performance evaluation, the current random forest model is used as the membrane fouling prediction model. Otherwise, the hyperparameters of the current random forest model are optimized, and the optimized random forest model is trained using the training set until it passes the performance evaluation. The random forest model that passes the performance evaluation is used as the membrane fouling prediction model.

[0016] In some implementations of the first aspect, the performance evaluation index used in the performance evaluation process is the determination coefficient R 2 And mean square error MSE.

[0017] In some implementations of the first aspect, the hyperparameters that need to be optimized are the number of trees and the number of features; the optimization range of the number of trees is 200-2400, with a step size of 200; the optimization range of the number of features is 0-7, with a step size of 1; the hyperparameters other than the number of trees and the number of features are the maximum depth of each decision tree, the minimum number of samples required for internal node re-division, and the minimum number of samples for leaf nodes; the value of the maximum depth of each decision tree is none; the value of the minimum number of samples required for internal node re-division is 2; the value of the minimum number of samples for leaf nodes is 1.

[0018] In some implementations of the first aspect, the method further includes:

[0019] Based on the membrane fouling prediction model, the feature importance corresponding to each EPS feature data is calculated using the average impurity reduction method.

[0020] In a second aspect, an embodiment of the present invention provides a membrane contamination prediction method based on extracellular polymer data-driven, the method comprising:

[0021] Obtain EPS characteristic data of anaerobic membrane bioreactor;

[0022] The EPS characteristic data is input into the membrane fouling prediction model, and the membrane fouling prediction model processes the EPS characteristic data to predict the membrane fouling rate of the anaerobic membrane bioreactor;

[0023] The membrane fouling prediction model is obtained based on the membrane fouling prediction model training method driven by extracellular polymer data as described above.

[0024] In a third aspect, an embodiment of the present invention provides a membrane fouling prediction model training device driven by extracellular polymer data, the device comprising:

[0025] An acquisition module is used to obtain characteristic data of extracellular polymers (EPS) and membrane fouling rate during the operation of the anaerobic membrane bioreactor;

[0026] A construction module is used to construct a data set based on multiple samples and their corresponding labels, using EPS characteristic data during the operation of the anaerobic membrane bioreactor as samples and the membrane fouling rate during the operation of the anaerobic membrane bioreactor as labels corresponding to the samples;

[0027] The training module is used to train the random forest model using the data set to obtain a membrane fouling prediction model.

[0028] In a fourth aspect, an embodiment of the present invention provides a membrane pollution prediction device driven by extracellular polymer data, the device comprising:

[0029] An acquisition module is used to obtain EPS characteristic data of the anaerobic membrane bioreactor;

[0030] A prediction module is used to input EPS characteristic data into a membrane fouling prediction model, and the membrane fouling prediction model processes the EPS characteristic data to predict the membrane fouling rate of the anaerobic membrane bioreactor;

[0031] The membrane fouling prediction model is obtained based on the membrane fouling prediction model training method driven by extracellular polymer data as described above.

[0032] In a fifth 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 as described above.

[0033] In a sixth 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.

[0034] In an embodiment of the present invention, EPS characteristic data and membrane fouling rate during the operation of an anaerobic membrane bioreactor can be obtained; the EPS characteristic data during the operation of the anaerobic membrane bioreactor is used as a sample, and the membrane fouling rate during the operation of the anaerobic membrane bioreactor is used as a label corresponding to the sample, and a data set is constructed according to multiple samples and their corresponding labels; the random forest model is trained using the data set to obtain a membrane fouling prediction model with the best prediction ability, and then the membrane fouling rate of the anaerobic membrane bioreactor is quickly and accurately predicted based on the model, thereby improving the membrane fouling prediction effect.

[0035] 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 easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] 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, wherein:

[0037] Figure 1 A flowchart of a membrane fouling prediction model training method based on extracellular polymer data-driven provided in an embodiment of the present invention;

[0038] Figure 2 A flowchart of a membrane fouling prediction method based on extracellular polymer data-driven provided in an embodiment of the present invention;

[0039] Figure 3 A schematic diagram of membrane fouling prediction performance provided by an embodiment of the present invention;

[0040] Figure 4 A schematic diagram of the importance of membrane fouling characteristics provided by an embodiment of the present invention;

[0041] Figure 5 A structural diagram of a membrane fouling prediction model training device driven by extracellular polymer data provided by an embodiment of the present invention;

[0042] Figure 6 A structural diagram of a membrane fouling prediction device driven by extracellular polymer data provided by an embodiment of the present invention;

[0043] Figure 7 The figure is a structural diagram of an exemplary electronic device capable of implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

[0045] In addition, the term "and / or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0046] In order to solve the technical problems arising from the background technology, the embodiments of the present invention provide a membrane pollution prediction method, device, equipment and storage medium driven by extracellular polymer data. Specifically, the EPS characteristic data and membrane pollution rate during the operation of the anaerobic membrane bioreactor are obtained; the EPS characteristic data during the operation of the anaerobic membrane bioreactor are used as samples, and the membrane pollution rate during the operation of the anaerobic membrane bioreactor is used as the label corresponding to the sample, and a data set is constructed according to multiple samples and their corresponding labels; the random forest model is trained using the data set to obtain a membrane pollution prediction model with the best prediction ability, and then the membrane pollution rate of the anaerobic membrane bioreactor is quickly and accurately predicted based on the model, thereby improving the membrane pollution prediction effect.

[0047] In conjunction with the accompanying drawings, a membrane fouling prediction method, device, equipment and storage medium based on extracellular polymer data-driven provided by an embodiment of the present invention are described in detail through specific embodiments.

[0048] Figure 1 A flowchart of a membrane fouling prediction model training method based on extracellular polymer data driven provided in an embodiment of the present invention, such as Figure 1 As shown, the membrane fouling prediction model training method 100 may include the following steps:

[0049] S110, obtaining EPS characteristic data and membrane fouling rate during the operation of the anaerobic membrane bioreactor.

[0050] In some embodiments, the digestion liquid during the operation of the anaerobic membrane bioreactor can be tested to obtain EPS characteristic data, wherein the EPS characteristic data may include: the protein concentration of the soluble EPS (S-EPSpn), the polysaccharide concentration of the soluble EPS (S-EPSps), the protein concentration of the loosely bound EPS (LB-EPSpn), the polysaccharide concentration of the loosely bound EPS (LB-EPSps), the protein concentration of the tightly bound EPS (TB-EPSpn), and the polysaccharide concentration of the tightly bound EPS (TB-EPSps).

[0051] In some embodiments, a digital pressure gauge may be used to monitor the membrane assembly during the operation of the anaerobic membrane bioreactor to obtain a membrane fouling rate, wherein the membrane fouling rate may include: a transmembrane pressure difference growth rate.

[0052] S120, taking the EPS characteristic data during the operation of the anaerobic membrane bioreactor as a sample, taking the membrane fouling rate during the operation of the anaerobic membrane bioreactor as a label corresponding to the sample, and constructing a data set according to multiple samples and their corresponding labels.

[0053] S130, using the data set to train the random forest model to obtain a membrane fouling prediction model.

[0054] In some embodiments, the data set can be preprocessed, and the preprocessed data set can be used to train the random forest model to obtain a membrane fouling prediction model. Preprocessing can include operations such as data cleaning and data normalization. The data cleaning here is used to clean useless information in the data set and perform noise reduction processing. Specifically, it can include missing value processing and outlier processing; the data normalization here is used to scale the data in the data set and unify it to a specific interval. Specifically, it can be achieved through a min-max normalization algorithm, a standard deviation normalization algorithm, or an L2-norm normalization algorithm, which is not limited here.

[0055] In some embodiments, the data set can be divided into a training set and a test set according to a preset ratio (for example, 4:1), the training set is used to train the random forest model, and the test set is used to perform performance evaluation on the trained random forest model. If the trained random forest model passes the performance evaluation, the current random forest model is used as the membrane contamination prediction model. Otherwise, the current random forest model is hyperparameter optimized, and the optimized random forest model is trained using the training set until it passes the performance evaluation, and the random forest model that passes the performance evaluation is used as the membrane contamination prediction model.

[0056] It is worth noting that in the performance evaluation process, the determination coefficient R 2The performance of the random forest model is evaluated using the mean square error (MSE) as the performance evaluation index. 2 The calculation formula for the mean square error MSE can be shown as follows:

[0057]

[0058] Where n is the number of samples, is the predicted value of membrane fouling rate of the i-th sample, y i is the actual value of membrane fouling rate of the ith sample, i.e., the label, and y is the average value of the actual value of membrane fouling rate.

[0059] At the same time, the hyperparameters that need to be optimized here are the number of trees (n_trees) and the number of features (n_features); the optimization range of the number of trees (n_trees) is 200-2400, with a step size of 200; the optimization range of the number of features (n_features) is 0-7, with a step size of 1. In addition to the number of trees (n_trees) and the number of features (n_features), the hyperparameters other than the number of trees (n_trees) and the number of features (n_features) are the maximum depth of each decision tree (max_depth), the minimum number of samples required for internal node re-division (min_samples_spilt), and the minimum number of samples of leaf nodes (min_samples_leaf); the value of the maximum depth of each decision tree (max_depth) is none; the value of the minimum number of samples required for internal node re-division (min_samples_spilt) is 2; the value of the minimum number of samples of leaf nodes (min_samples_leaf) is 1.

[0060] After obtaining the membrane pollution prediction model, the feature importance corresponding to each EPS feature data, that is, the membrane pollution contribution weight, can be calculated based on the membrane pollution prediction model using the average impurity reduction method, and then sorted to determine the key feature data affecting membrane pollution, that is, the key influencing factors of membrane pollution, to complete the membrane pollution diagnosis.

[0061] Based on the membrane pollution prediction model training method 100 provided in the embodiment of the present invention, the embodiment of the present invention also provides a membrane pollution prediction method driven by extracellular polymer data, such as Figure 2 As shown, the membrane fouling prediction method 200 may include the following steps:

[0062] S210, obtaining EPS characteristic data of the anaerobic membrane bioreactor.

[0063] S220, inputting the EPS characteristic data into a membrane fouling prediction model, and the membrane fouling prediction model processes the EPS characteristic data to predict the membrane fouling rate of the anaerobic membrane bioreactor.

[0064] The membrane fouling prediction model is obtained based on the membrane fouling prediction model training method 100 as described above.

[0065] For ease of understanding, the above content is described below in conjunction with a specific embodiment:

[0066] (1) The digestion liquid during the operation of the anaerobic membrane bioreactor was tested to obtain EPS characteristic data, including: the protein concentration of soluble EPS (S-EPSpn), the polysaccharide concentration of soluble EPS (S-EPSps), the protein concentration of loosely bound EPS (LB-EPSpn), the polysaccharide concentration of loosely bound EPS (LB-EPSps), the protein concentration of tightly bound EPS (TB-EPSpn), and the polysaccharide concentration of tightly bound EPS (TB-EPSps).

[0067] (2) The membrane components in the anaerobic membrane bioreactor are monitored by a digital pressure gauge to obtain the membrane fouling rate, wherein the membrane fouling rate includes: the transmembrane pressure difference growth rate.

[0068] (3) Taking the EPS characteristic data during the operation of the anaerobic membrane bioreactor as samples and the membrane fouling rate during the operation of the anaerobic membrane bioreactor as the label corresponding to the sample, a data set is constructed based on multiple samples and their corresponding labels.

[0069] (4) Preprocess the data set, and then divide the preprocessed data set into a training set and a test set according to a ratio of 4:1. Use the training set to train the random forest model, and use the test set to evaluate the performance of the trained random forest model and calculate the determination coefficient R 2 And mean square error MSE, if R 2 ≥0.85, MSE≤0.2, it is determined that the trained random forest model has passed the performance evaluation, and the current random forest model is used as the membrane fouling prediction model. Otherwise, the random forest model is hyperparameter optimized, and the optimized random forest model is trained using the training set until it passes the performance evaluation. The random forest model that passes the performance evaluation is used as the membrane fouling prediction model.

[0070] As an example, Figure 3 As shown in the figure, if the predicted value of membrane fouling rate output by the current random forest model is R 2 =0.919, MSE=0.079, indicating that the current random forest model passes the performance evaluation.

[0071] (5) The obtained EPS characteristic data of the anaerobic membrane bioreactor is input into the membrane fouling prediction model, and the membrane fouling prediction model processes the EPS characteristic data to predict the membrane fouling rate of the anaerobic membrane bioreactor.

[0072] (6) Based on the membrane fouling prediction model, the feature importance corresponding to each EPS feature data is calculated using the average impurity reduction method, and then ranked accordingly, such as Figure 4 As shown, the feature importance corresponding to the EPS feature data is from high to low: TB-EPSpn, TB-EPSps, LB-EPSpn, S-EPSps, S-EPSpn, LB-EPSps. Here, the key feature data affecting membrane fouling is determined to be TB-EPSpn, and the membrane fouling diagnosis is completed.

[0073] In summary, according to the embodiments of the present invention, at least the following technical effects are achieved:

[0074] The EPS characteristic data during the operation of the anaerobic membrane bioreactor is used as a sample, and the membrane fouling rate during the operation of the anaerobic membrane bioreactor is used as the label corresponding to the sample to train the random forest model, so as to effectively analyze the nonlinear relationship between EPS and membrane fouling, and obtain the membrane fouling prediction model with the best prediction ability. Then, based on the model, the membrane fouling rate of the anaerobic membrane bioreactor, that is, the membrane fouling process, is predicted quickly and accurately, thereby improving the membrane fouling prediction effect. In addition, the model can be used to effectively diagnose membrane fouling.

[0075] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0076] The above is an introduction to a method embodiment. The following is a further explanation of the solution of the present invention through an apparatus embodiment.

[0077] Figure 5 A structural diagram of a membrane fouling prediction model training device driven by extracellular polymer data provided by an embodiment of the present invention, such as Figure 5 As shown, the membrane fouling prediction model training device 500 may include:

[0078] The acquisition module 510 is used to obtain characteristic data of extracellular polymers (EPS) and membrane fouling rate during the operation of the anaerobic membrane bioreactor.

[0079] The construction module 520 is used to construct a data set based on multiple samples and their corresponding labels, using the EPS characteristic data during the operation of the anaerobic membrane bioreactor as samples and the membrane fouling rate during the operation of the anaerobic membrane bioreactor as labels corresponding to the samples.

[0080] The training module 530 is used to train the random forest model using the data set to obtain a membrane fouling prediction model.

[0081] Understandably, Figure 5 Each module / unit in the membrane fouling prediction model training device 500 has the following functions: Figure 1 The functions of the various steps in the membrane fouling prediction model training method 100 shown in the figure can achieve their corresponding technical effects, and for the sake of brevity, they will not be repeated here.

[0082] Figure 6 A structural diagram of a membrane fouling prediction device driven by extracellular polymer data provided by an embodiment of the present invention, such as Figure 6 As shown, the membrane fouling prediction device 600 may include:

[0083] The acquisition module 610 is used to acquire EPS characteristic data of the anaerobic membrane bioreactor.

[0084] The prediction module 620 is used to input the EPS characteristic data into the membrane fouling prediction model, and the membrane fouling prediction model processes the EPS characteristic data to predict the membrane fouling rate of the anaerobic membrane bioreactor.

[0085] The membrane fouling prediction model is obtained based on the membrane fouling prediction model training method 100 as described above.

[0086] Understandably, Figure 6 Each module / unit in the membrane fouling prediction device 600 shown has the function of realizing Figure 2 The functions of the various steps in the membrane fouling prediction method 200 shown can achieve their corresponding technical effects, and for the sake of brevity, they will not be repeated here.

[0087] Figure 7 700 is a block diagram of an exemplary electronic device capable of implementing an embodiment of the present invention. Electronic device 700 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 700 may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown in the present invention, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required in the present invention.

[0088] like Figure 7As shown, the electronic device 700 may include a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 may also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0089] Multiple components in the electronic device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0090] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 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 running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as method 100 or method 200. For example, in some embodiments, method 100 or method 200 may be implemented as a computer program product, including a computer program, which is tangibly contained in a computer-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the method 100 or method 200 described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to execute the method 100 or the method 200 in any other appropriate manner (eg, by means of firmware).

[0091] 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), load 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, which may be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general programmable processor, which may 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.

[0092] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes 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 the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0093] In the context of the present invention, a computer-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a computer-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0094] 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 or method 200 and achieve the corresponding technical effects achieved by executing the methods in the embodiments of the present invention. For the sake of concise description, they will not be repeated here.

[0095] 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 or the method 200 is implemented.

[0096] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and the present invention is not limited here.

[0097] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A membrane fouling prediction model training method based on extracellular polymer data driven, characterized in that: The method comprises: Obtain EPS characteristic data and membrane fouling rate during the operation of anaerobic membrane bioreactor; Taking the EPS characteristic data during the operation of the anaerobic membrane bioreactor as samples, and the membrane fouling rate during the operation of the anaerobic membrane bioreactor as the label corresponding to the sample, a data set is constructed based on multiple samples and their corresponding labels; The random forest model is trained using the data set to obtain a membrane fouling prediction model.

2. The method according to claim 1, characterized in that: The method of obtaining EPS characteristic data and membrane fouling rate during the operation of the anaerobic membrane bioreactor includes: The digestate during the operation of the anaerobic membrane bioreactor was tested to obtain EPS characteristic data; The transmembrane pressure difference of the membrane module during the operation of the anaerobic membrane bioreactor is monitored to obtain the membrane fouling rate.

3. The method according to claim 2, characterized in that The EPS characteristic data include: protein concentration of soluble EPS, polysaccharide concentration of soluble EPS, protein concentration of loosely bound EPS, polysaccharide concentration of loosely bound EPS, protein concentration of tightly bound EPS, polysaccharide concentration of tightly bound EPS; the membrane fouling rate includes: transmembrane pressure difference growth rate (kPa / d).

4. The method according to claim 3, characterized in that The random forest model is trained using the data set to obtain a membrane fouling prediction model, including: Dividing the data set into a training set and a test set according to a preset ratio; Using the training set to train the random forest model, and using the test set to evaluate the performance of the trained random forest model; If the trained random forest model passes the performance evaluation, the current random forest model is used as the membrane fouling prediction model. Otherwise, the hyperparameters of the current random forest model are optimized, and the optimized random forest model is trained using the training set until it passes the performance evaluation. The random forest model that passes the performance evaluation is used as the membrane fouling prediction model.

5. The method according to claim 4, characterized in that The performance evaluation index used in the performance evaluation process is the determination coefficient R 2 And mean square error MSE.

6. The method according to claim 4, characterized in that The hyperparameters that need to be optimized are the number of trees and the number of features; The optimization range of the number of trees is 200-2400, with a step size of 200; the optimization range of the number of features is 0-7, with a step size of 1; the hyperparameters other than the number of trees and features are the maximum depth of each decision tree, the minimum number of samples required for internal node repartitioning, and the minimum number of samples for leaf nodes; the maximum depth of each decision tree is none; the minimum number of samples required for internal node repartitioning is 2; and the minimum number of samples for leaf nodes is 1.

7. The method according to claim 4, characterized in that The method further comprises: Based on the membrane fouling prediction model, the feature importance corresponding to each EPS feature data is calculated using the average impurity reduction method.

8. A membrane fouling prediction method based on extracellular polymer data driven, characterized in that: The method comprises: Obtain EPS characteristic data of anaerobic membrane bioreactor; The EPS characteristic data is input into a membrane fouling prediction model, and the membrane fouling prediction model processes the EPS characteristic data to predict the membrane fouling rate of the anaerobic membrane bioreactor; Wherein, the membrane pollution prediction model is obtained based on the membrane pollution prediction model training method driven by extracellular polymer data as described in any one of claims 1-7.

9. A membrane fouling prediction model training device driven by extracellular polymer data, characterized in that: The device comprises: An acquisition module is used to obtain characteristic data of extracellular polymers (EPS) and membrane fouling rate during the operation of the anaerobic membrane bioreactor; A construction module is used to construct a data set based on multiple samples and their corresponding labels, using EPS characteristic data during the operation of the anaerobic membrane bioreactor as samples and the membrane fouling rate during the operation of the anaerobic membrane bioreactor as labels corresponding to the samples; The training module is used to train the random forest model using the data set to obtain a membrane fouling prediction model.

10. A membrane fouling prediction device driven by extracellular polymer data, characterized in that: The device comprises: An acquisition module is used to obtain EPS characteristic data of the anaerobic membrane bioreactor; A prediction module, used for inputting the EPS characteristic data into a membrane fouling prediction model, and processing the EPS characteristic data by the membrane fouling prediction model to predict the membrane fouling rate of the anaerobic membrane bioreactor; Wherein, the membrane pollution prediction model is obtained based on the membrane pollution prediction model training method driven by extracellular polymer data as described in any one of claims 1-7.

Images