Membrane fouling rate prediction method and device for anaerobic membrane bioreactor

Abstract

The embodiment of the present disclosure provides a membrane fouling rate prediction method and device for an anaerobic membrane bioreactor, and relates to the technical field of wastewater treatment. The method comprises the following steps: obtaining a sample set, wherein the samples in the sample set take the operation parameters, biomass parameters and membrane component parameters of the anaerobic membrane bioreactor as sample features, and take the membrane fouling rate of the anaerobic membrane bioreactor as a sample label; pre-processing the sample set to obtain a pre-processed sample set; training a neural network according to the pre-processed sample set to obtain a membrane fouling rate prediction model with strong prediction ability, and then rapidly and accurately predicting the membrane fouling rate based on the model, thereby effectively improving the membrane fouling rate prediction effect.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of sewage treatment, and particularly relates to a membrane fouling rate prediction method and device for an anaerobic membrane bioreactor. BACKGROUND

[0002] An anaerobic membrane bioreactor (AnMBR) is a new sewage treatment technology combining anaerobic biological treatment with membrane separation process, which can effectively retain anaerobic functional microorganisms, improve organic matter degradation efficiency and operation stability. The AnMBR has become one of the most promising sewage treatment technologies due to its excellent effluent water quality, efficient resource recovery rate and smaller land occupation area.

[0003] Membrane fouling can cause the transmembrane pressure difference to rise, the membrane flux to decrease, and further cause the membrane cleaning or component replacement frequency to increase, resulting in reduced sewage treatment capacity and increased operation cost. Therefore, membrane fouling rate prediction is of great significance for ensuring the operation stability of the AnMBR, achieving early warning of membrane fouling, analyzing the membrane fouling mechanism, and developing membrane fouling control measures.

[0004] At present, the traditional membrane fouling rate prediction scheme generally has large errors and poor effects. Therefore, how to improve the membrane fouling rate prediction effect has become a technical problem to be solved. SUMMARY

[0005] Embodiments of the present disclosure provide a membrane fouling rate prediction method and device, equipment and storage medium for an anaerobic membrane bioreactor.

[0006] In a first aspect, embodiments of the present disclosure provide a training method of a membrane fouling rate prediction model for an anaerobic membrane bioreactor, and the method comprises:

[0007] obtaining a sample set, wherein samples in the sample set take the operation parameters, biomass parameters and membrane component parameters of the anaerobic membrane bioreactor as sample features, and take the membrane fouling rate of the anaerobic membrane bioreactor as a sample label;

[0008] preprocessing the sample set to obtain a preprocessed sample set;

[0009] training a neural network according to the preprocessed sample set to obtain the membrane fouling rate prediction model.

[0010] In some implementable manners of the first aspect, the sample set is obtained, comprising:

[0011] screening a plurality of groups of information from a plurality of anaerobic membrane bioreactor files, wherein each group of information comprises: an operating parameter of the anaerobic membrane bioreactor, a biomass parameter, a membrane module parameter, a membrane fouling rate;

[0012] constructing a sample according to each group of information, and generating a sample set according to each sample.

[0013] In some implementable manners of the first aspect, the operating parameter comprises: an organic load, an influent chemical oxygen demand concentration, a biomass backwash rate, a hydraulic retention time;

[0014] The biomass parameter comprises: a volatile solid concentration, a soluble microbial product protein concentration, a soluble microbial product polysaccharide concentration, a soluble microbial product protein to polysaccharide ratio, an extracellular polymeric substance protein concentration, an extracellular polymeric substance polysaccharide concentration, an extracellular polymeric substance protein to polysaccharide ratio;

[0015] The membrane module parameter comprises: a membrane pore size, a membrane packing density, a membrane flux.

[0016] In some implementable manners of the first aspect, the sample set is preprocessed, comprising:

[0017] data cleaning is performed on the sample set;

[0018] data normalization is performed on the sample set after data cleaning.

[0019] In some implementable manners of the first aspect, the data cleaning on the sample set comprises:

[0020] missing value processing and outlier processing are performed on each sample in the sample set.

[0021] In some implementable manners of the first aspect, the neural network is trained according to the preprocessed sample set to obtain a membrane fouling rate prediction model, comprising:

[0022] the preprocessed sample set is divided into a training set and a test set;

[0023] the neural network is trained according to the training set, and the trained neural network is performance evaluated according to the test set;

[0024] if the trained neural network passes the performance evaluation, the trained neural network is taken as the membrane fouling rate prediction model;

[0025] if the trained neural network does not pass the performance evaluation, the hyperparameters of the current neural network are adjusted, and the adjusted neural network is trained according to the training set until the performance evaluation is passed, and the neural network that passes the performance evaluation is taken as the membrane fouling rate prediction model.

[0026] In some possible implementation manners of the first aspect, the neural network comprises one input layer, two hidden layers, and one output layer.

[0027] The number of neurons of the input layer is 14, the number of neurons of the first hidden layer is 9, the number of neurons of the second hidden layer is 6, and the number of neurons of the output layer is 1.

[0028] In a second aspect, the embodiments of the present disclosure provide a membrane fouling rate prediction method for an anaerobic membrane bioreactor, the method comprising:

[0029] obtaining operation parameters, biomass parameters, and membrane component parameters of the anaerobic membrane bioreactor to be predicted;

[0030] inputting the operation parameters, the biomass parameters, and the membrane component parameters into a membrane fouling rate prediction model to obtain the membrane fouling rate of the anaerobic membrane bioreactor to be predicted;

[0031] The membrane fouling rate prediction model is obtained based on the training method of the membrane fouling rate prediction model.

[0032] In a third aspect, the embodiments of the present disclosure provide a training device for a membrane fouling rate prediction model of an anaerobic membrane bioreactor, the device comprising:

[0033] an obtaining module configured to obtain a sample set, wherein samples in the sample set take operation parameters, biomass parameters, and membrane component parameters of an anaerobic membrane bioreactor as sample features and take a membrane fouling rate of the anaerobic membrane bioreactor as a sample label;

[0034] a preprocessing module configured to preprocess the sample set to obtain a preprocessed sample set;

[0035] a training module configured to train a neural network according to the preprocessed sample set to obtain a membrane fouling rate prediction model.

[0036] In a fourth aspect, the embodiments of the present disclosure provide a membrane fouling rate prediction device for an anaerobic membrane bioreactor, the device comprising:

[0037] an obtaining module configured to obtain operation parameters, biomass parameters, and membrane component parameters of an anaerobic membrane bioreactor to be predicted;

[0038] a prediction module configured to input the operation parameters, the biomass parameters, and the membrane component parameters into a membrane fouling rate prediction model to obtain a membrane fouling rate of the anaerobic membrane bioreactor to be predicted;

[0039] The membrane fouling rate prediction model is obtained based on the training method of the membrane fouling rate prediction model.

[0040] In a fifth aspect, an electronic device is provided, including: at least one processor; and a memory communicatively connected with 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 to enable the at least one processor to perform the method described above.

[0041] In a sixth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, the computer instructions being used to cause a computer to perform the method described above.

[0042] In the embodiments of the present disclosure, a sample set can be acquired, wherein samples in the sample set take the operation parameters of the anaerobic membrane bioreactor, the biomass parameters, and the membrane module parameters as sample features, and take the membrane fouling rate of the anaerobic membrane bioreactor as a sample label; the sample set is preprocessed to obtain a preprocessed sample set; the neural network is trained according to the preprocessed sample set to obtain a membrane fouling rate prediction model with strong prediction ability, and then the membrane fouling rate is quickly and accurately predicted based on the model, and the membrane fouling rate prediction effect is effectively improved.

[0043] It should be understood that the content described in the summary section is not intended to limit the key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0044] The above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent by describing in detail the following embodiments with reference to the attached drawings. The attached drawings are intended to better understand the present disclosure and do not limit the present disclosure. In the drawings, the same or similar elements are denoted by the same or similar reference numerals, and:

[0045] Figure 1 A flowchart of a training method of a membrane fouling rate prediction model is shown, which is provided by the embodiments of the present disclosure;

[0046] Figure 2 A flowchart of a membrane fouling rate prediction method is shown, which is provided by the embodiments of the present disclosure;

[0047] Figure 3 A structural diagram of a training device of a membrane fouling rate prediction model is shown, which is provided by the embodiments of the present disclosure;

[0048] Figure 4 A structural diagram of a membrane fouling rate prediction device is shown, which is provided by the embodiments of the present disclosure;

[0049] Figure 5 A structural diagram of an exemplary electronic device capable of implementing the embodiments of the present disclosure is shown. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0051] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0052] To address the problems in the background art, embodiments of this disclosure provide a method and apparatus for predicting membrane fouling rates in anaerobic membrane bioreactors. Specifically, a sample set is obtained, wherein the samples in the sample set are characterized by the operating parameters, biomass parameters, and membrane module parameters of the anaerobic membrane bioreactor, and labeled with the membrane fouling rate of the anaerobic membrane bioreactor; the sample set is preprocessed to obtain a preprocessed sample set; a neural network is trained based on the preprocessed sample set to obtain a membrane fouling rate prediction model with strong predictive ability, and then the membrane fouling rate is quickly and accurately predicted based on this model, effectively improving the membrane fouling rate prediction effect.

[0053] The method and apparatus for predicting membrane fouling rates in anaerobic membrane bioreactors provided in this disclosure will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0054] Figure 1 A flowchart illustrating a training method for a membrane fouling rate prediction model for an anaerobic membrane bioreactor, as provided in an embodiment of this disclosure, is shown. Figure 1 As shown, training method 100 may include the following steps:

[0055] S110, Obtain the sample set.

[0056] The sample set is characterized by the operating parameters, biomass parameters, and membrane module parameters of the anaerobic membrane bioreactor, and labeled by the membrane fouling rate of the anaerobic membrane bioreactor.

[0057] As an example, operating parameters may include, but are not limited to: organic load, influent chemical oxygen demand concentration, biogas recirculation rate, and hydraulic retention time.

[0058] The biomass parameters can include, but are not limited to, volatile solid concentration, soluble microbial product protein concentration, soluble microbial product polysaccharide concentration, soluble microbial product protein to polysaccharide ratio, extracellular polymeric substance protein concentration, extracellular polymeric substance polysaccharide concentration, and extracellular polymeric substance protein to polysaccharide ratio.

[0059] The membrane assembly parameters can include, but are not limited to, membrane pore size, membrane packing density, and membrane flux.

[0060] In some embodiments, a plurality of groups of information can be screened from a plurality of anaerobic membrane bioreactor files.

[0061] Each group of information includes operating parameters of the anaerobic membrane bioreactor, biomass parameters, membrane assembly parameters, and membrane fouling rate.

[0062] For example, a plurality of published literatures can be crawled from a plurality of websites such as encyclopedic websites, paper websites, websites of manufacturers of anaerobic membrane bioreactors, and / or technical forums, and then a plurality of groups of information can be screened from texts, tables, and illustrations of the plurality of published literatures.

[0063] A corresponding sample is constructed according to each group of information, and a sample set is generated according to the samples.

[0064] In this way, a sample set with a large number of samples can be quickly obtained, facilitating subsequent training of a membrane fouling rate prediction model.

[0065] S120, preprocessing the sample set to obtain a preprocessed sample set.

[0066] In some embodiments, the preprocessing can include data cleaning and data normalization.

[0067] The data cleaning is used to clean useless information of sample features in the sample set and perform noise reduction processing, and specifically, can include missing value processing and outlier processing; and the data normalization is used to perform data scaling on the sample features in the sample set and unify to a specific interval, and specifically, can be implemented by a min-max normalization algorithm, a standard deviation normalization algorithm, or an L2-norm normalization algorithm, without limitation.

[0068] That is, the sample set can be subjected to data cleaning (e.g., missing value processing and outlier processing), and the sample set after data cleaning can be subjected to data normalization to obtain a preprocessed sample set.

[0069] Obviously, the quality of the sample set is high at this time, facilitating subsequent training of a membrane fouling rate prediction model.

[0070] S130, training a neural network according to the preprocessed sample set to obtain a membrane fouling rate prediction model.

[0071] In some embodiments, the pre-processed sample set can be divided into a training set and a test set.

[0072] For example, 80% of the samples in the pre-processed sample set can be randomly set as the training set, and 20% of the samples can be set as the test set, that is, the samples in the pre-processed sample set are randomly divided into the training set and the test set at a ratio of 4:1.

[0073] The neural network is trained according to the training set, and the trained neural network is performance evaluated according to the test set.

[0074] The neural network is built based on the Matlab programming language, and the basic architecture includes an input layer, a hidden layer, and an output layer. The transfer function of the hidden layer is set to the tangent S-shaped transfer function, also known as tansig, and its expression is as follows:

[0075]

[0076] For example, when the neural network is trained according to the training set, the training stop condition can be that the loss value is less than a preset threshold, or the number of iterations reaches a specified number. When the training stop condition is met, the performance of the current, i.e., the trained, neural network is evaluated according to the test set.

[0077] The trained neural network can be performance evaluated using the mean square error (MSE) and the goodness of fit (R 2 , and its expression is as follows:

[0078]

[0079]

[0080] , where n is the number of samples, is the predicted membrane fouling rate of the i-th sample (i.e., the membrane fouling rate output by the neural network), y i is the actual value of the membrane fouling rate of the i-th sample (i.e., the sample label), is the average value of the actual value of the membrane fouling rate of the sample.

[0081] If the trained neural network passes the performance evaluation, the trained neural network is used as a membrane fouling rate prediction model; if the trained neural network fails the performance evaluation, the hyperparameters of the current neural network are adjusted, and the adjusted neural network is trained according to the training set until it passes the performance evaluation. The neural network that passes the performance evaluation is used as a membrane fouling rate prediction model.

[0082] For example, if the trained neural network corresponds to R 2≥ 0.70 and MSE < 0.2, such as R 2 = 0.800, MSE = 0.118, it is taken as the membrane fouling rate prediction model. Otherwise, the hyperparameters of the current neural network are adjusted, and training is performed again until it passes the performance evaluation. The neural network that passes the performance evaluation is taken as the membrane fouling rate prediction model.

[0083] Optionally, the initial parameters of the neural network, i.e., the initial weights and initial biases of the neural network, are randomly assigned by the computer; the hyperparameters of the neural network can include: the number of neural network layers, the number of hidden layer neurons, epochs, learning rate, target error, maximum momentum, etc. The epochs of the neural network can be set to 1000 times, the learning rate is set to 0.1, the target error is set to 1x10 -6 , and the maximum momentum is set to 1x10 10 . As for the number of neural network layers and the number of hidden layer neurons, they are the hyperparameters that need to be adjusted.

[0084] It should be noted that when adjusting the hyperparameters as described above, the number of neural network layers and the number of hidden layer neurons in the neural network can be adjusted by manually adjusting the hyperparameters.

[0085] For example, the number of hidden layer neurons of the neural network can be determined by the following formula:

[0086]

[0087] where n is the number of input layer neurons; and a is a constant between 1 and 10.

[0088] The neural network can include one input layer, two hidden layers, and one output layer. According to the number of input features and output features, the number of input layer neurons is set to 14, the number of output layer neurons is set to 1, the number of first layer hidden layer neurons is in the range of 5-15, and the number of second layer hidden layer neurons is in the range of 0-15.

[0089] After continuously adjusting the hyperparameters, it is determined that the number of neurons in the input layer of the neural network is 14, the number of neurons in the first layer hidden layer is 9, the number of neurons in the second layer hidden layer is 6, and the number of neurons in the output layer is 1, the training effect of the neural network is best.

[0090] In other embodiments, a user can directly set ideal hyperparameters for the neural network model according to experience, train the neural network according to the preprocessed sample set, and take the neural network that meets the training stopping condition as the membrane fouling rate prediction model.

[0091] In the embodiments of the present disclosure, the sample set can be preprocessed, and a neural network with good generalization ability and strong robustness is trained according to the preprocessed sample set to obtain a membrane fouling rate prediction model with strong prediction ability.

[0092] Based on the training method 100 for the membrane fouling rate prediction model of the anaerobic membrane bioreactor provided by the embodiments of the present disclosure, the embodiments of the present disclosure also provide a membrane fouling rate prediction method for the anaerobic membrane bioreactor. Figure 2 As shown in the method 200 for predicting the membrane fouling rate, the method can include the following steps:

[0093] S210, obtaining operation parameters, biomass parameters and membrane component parameters of an anaerobic membrane bioreactor to be predicted.

[0094] S220, inputting the operation parameters, the biomass parameters and the membrane component parameters into the membrane fouling rate prediction model to obtain a membrane fouling rate of the anaerobic membrane bioreactor to be predicted.

[0095] The membrane fouling rate prediction model is obtained based on the training method of the membrane fouling rate prediction model as described above.

[0096] In the embodiments of the present disclosure, the membrane fouling rate can be quickly and accurately predicted based on the membrane fouling rate prediction model with strong prediction ability, and the effect of the membrane fouling rate prediction can be effectively improved.

[0097] In some embodiments, it can be determined whether the membrane fouling rate is greater than a preset threshold value, and if the membrane fouling rate is greater than the preset threshold value, an alarm information is generated and displayed to the user, so as to quickly warn and reduce the loss.

[0098] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present disclosure is not limited to the action sequence described, because according to the present disclosure, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should 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 disclosure.

[0099] The above is the introduction of the method embodiments, and the scheme described in the present disclosure will be further described through the device embodiments.

[0100] Figure 3 As shown in FIG. 3, a structure diagram of a training device for a membrane fouling rate prediction model of an anaerobic membrane bioreactor is shown, and the training device 300 can include: Figure 3

[0101] ​The acquisition module 310 is configured to acquire a sample set, wherein samples in the sample set take operating parameters, biomass parameters, and membrane assembly parameters of the anaerobic membrane bioreactor as sample features, and take a membrane fouling rate of the anaerobic membrane bioreactor as a sample label.

[0102] The preprocessing module 320 is configured to preprocess the sample set to obtain a preprocessed sample set.

[0103] The training module 330 is configured to train the neural network according to the preprocessed sample set to obtain a membrane fouling rate prediction model.

[0104] In some embodiments, the acquisition module 310 is specifically configured to:

[0105] filter a plurality of groups of information from a plurality of anaerobic membrane bioreactor files, wherein each group of information includes operating parameters, biomass parameters, membrane assembly parameters, and a membrane fouling rate of the anaerobic membrane bioreactor;

[0106] construct samples according to each group of information, and generate a sample set according to the samples.

[0107] In some embodiments, the operating parameters include an organic load, an influent chemical oxygen demand concentration, a biomass backwashing rate, and a hydraulic retention time.

[0108] The biomass parameters include a volatile solid concentration, a soluble microbial product protein concentration, a soluble microbial product polysaccharide concentration, a soluble microbial product protein-to-polysaccharide ratio, an extracellular polymeric substance protein concentration, an extracellular polymeric substance polysaccharide concentration, and an extracellular polymeric substance protein-to-polysaccharide ratio.

[0109] The membrane assembly parameters include a membrane pore size, a membrane packing density, and a membrane flux.

[0110] In some embodiments, the preprocessing module 320 is specifically configured to:

[0111] perform data cleaning on the sample set;

[0112] perform data normalization on the sample set after data cleaning.

[0113] In some embodiments, the preprocessing module 320 is specifically configured to:

[0114] perform missing value processing and outlier processing on each sample in the sample set.

[0115] In some embodiments, the training module 330 is specifically configured to:

[0116] divide the preprocessed sample set into a training set and a test set;

[0117] The neural network is trained according to the training set, and the trained neural network is evaluated according to the test set;

[0118] If the trained neural network passes the performance evaluation, the trained neural network is used as a membrane fouling rate prediction model.

[0119] If the trained neural network does not pass the performance evaluation, the hyperparameters of the current neural network are adjusted, and the adjusted neural network is trained according to the training set until it passes the performance evaluation. The neural network that passes the performance evaluation is used as a membrane fouling rate prediction model.

[0120] In some embodiments, the neural network includes one input layer, two hidden layers, and one output layer. The number of neurons in the input layer is 14, the number of neurons in the first hidden layer is 9, the number of neurons in the second hidden layer is 6, and the number of neurons in the output layer is 1.

[0121] It can be understood that, Figure 3 Each module / unit in the training device 300 shown has the function of implementing Figure 1 Each step in the training method 100 shown has the function of achieving its corresponding technical effect, and the corresponding technical effect is achieved. For the sake of brevity, it will not be repeated here.

[0122] Figure 4 A structural diagram of a membrane fouling rate prediction device for an anaerobic membrane bioreactor is shown, which is provided by an embodiment of the present disclosure, as shown in Figure 4 As shown, the membrane fouling rate prediction device 400 can include:

[0123] The acquisition module 410 is configured to acquire operation parameters, biomass parameters, and membrane component parameters of an anaerobic membrane bioreactor to be predicted.

[0124] The prediction module 420 is configured to input the operation parameters, the biomass parameters, and the membrane component parameters into a membrane fouling rate prediction model to obtain a membrane fouling rate of the anaerobic membrane bioreactor to be predicted.

[0125] The membrane fouling rate prediction model is obtained based on the training method described above.

[0126] In some embodiments, the membrane fouling rate prediction device 400 further includes:

[0127] The warning module is configured to determine whether the membrane fouling rate is greater than a preset threshold. If the membrane fouling rate is greater than the preset threshold, an alarm information is generated and displayed to a user for quick warning.

[0128] It can be understood that, Figure 4 Each module / unit in the membrane fouling rate prediction device 400 shown has the function of implementing Figure 2The functions of each step in the illustrated membrane fouling rate prediction method 200 and the corresponding technical effects achieved thereby are not repeated here for the sake of brevity.

[0129] Figure 5 A block diagram illustrating an example electronic device in which an embodiment of the present disclosure can be implemented is shown. The electronic device 500 is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device 500 can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present disclosure described and / or claimed in this document.

[0130] As shown, Figure 5 The electronic device 500 can include a computing unit 501 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 502 or a computer program loaded into a random access memory (RAM) 503 from a storage unit 508. Various programs and data required for the operation of the electronic device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0131] Various components in the electronic device 500 are connected to the I / O interface 505, including an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, a speaker, etc.; the storage unit 508, such as a magnetic disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0132] The computing unit 501 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs various methods and processes described above, such as the method 100 or the method 200. For example, in some embodiments, the method 100 or the method 200 can be implemented as a computer program product, including a computer program tangibly embodied in a computer-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded onto the RAM 503 and executed by the computing unit 501, one or more steps of the method 100 or the method 200 described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the method 100 or the method 200 by any other appropriate means, such as by means of firmware.

[0133] The various implementations described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a special-purpose standard product (ASSP), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0134] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0135] In the context of the present disclosure, a computer-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer-readable storage medium will include one or more of: a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0136] It should be noted that the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to make a computer execute the method 100 or the method 200, and achieve the corresponding technical effects achieved by the embodiments of the present disclosure executing the methods thereof. For brevity, the description will not be repeated here.

[0137] In addition, the present disclosure also provides a computer program product, which includes a computer program, and the computer program, when executed by a processor, implements the method 100 or the method 200.

[0138] To provide for interaction with a user, the above described embodiments can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0139] The embodiments described above can be implemented in a computing system that includes a back end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here, or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0140] The computer system can include clients and servers. The clients and the servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0141] It should be understood that the various forms of flow shown in the figures can be re-ordered, added to, or deleted from without departing from the spirit and scope of the present disclosure. For example, the steps recited in the disclosure can be executed in parallel, executed in sequence, or executed in different orders, as long as the desired results of the technology disclosed in the disclosure are achieved, and the present disclosure is not limited herein.

[0142] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and scope of the disclosure. Any modifications, equivalent substitutions, improvements, and the like, made within the spirit and principles of the disclosure, should be included in the scope of the disclosure.

Claims

1. A training method for a membrane fouling rate prediction model for anaerobic membrane bioreactors, characterized in that, The method includes: Obtain a sample set, wherein the samples in the sample set are characterized by the operating parameters, biomass parameters, and membrane module parameters of the anaerobic membrane bioreactor, and are labeled by the membrane fouling rate of the anaerobic membrane bioreactor. The sample set is preprocessed to obtain a preprocessed sample set; The neural network was trained based on the preprocessed sample set to obtain a membrane fouling rate prediction model; The operating parameters include: organic load, influent chemical oxygen demand concentration, biogas recirculation rate, and hydraulic retention time; The biomass parameters include: volatile solids concentration, soluble microbial product protein concentration, soluble microbial product polysaccharide concentration, soluble microbial product protein to polysaccharide ratio, extracellular polymeric protein concentration, extracellular polymeric polysaccharide concentration, and extracellular polymeric protein to polysaccharide ratio. The membrane module parameters include: membrane pore size, membrane packing density, and membrane flux.

2. The method according to claim 1, characterized in that, The acquisition of the sample set includes: Multiple sets of information were selected from various anaerobic membrane bioreactor files. Each set of information included: the operating parameters of the anaerobic membrane bioreactor, biomass parameters, membrane module parameters, and membrane fouling rate. Samples are constructed based on each set of information, and the sample set is generated based on each sample.

3. The method according to claim 1, characterized in that, The preprocessing of the sample set includes: Perform data cleaning on the sample set; Normalize the data after cleaning the sample set.

4. The method according to claim 3, characterized in that, The data cleaning of the sample set includes: Missing values ​​and outliers are handled for each sample in the sample set.

5. The method according to claim 1, characterized in that, The step of training the neural network based on the preprocessed sample set to obtain a membrane fouling rate prediction model includes: The preprocessed sample set is divided into a training set and a test set; The neural network is trained using the training set, and its performance is evaluated using the test set. If the trained neural network passes the performance evaluation, it will be used as a model for predicting membrane fouling rates. If the trained neural network fails the performance evaluation, the hyperparameters of the current neural network are adjusted, and the adjusted neural network is trained according to the training set until it passes the performance evaluation. The neural network that passes the performance evaluation is then used as the membrane fouling rate prediction model.

6. The method according to claim 1, characterized in that, The neural network includes one input layer, two hidden layers, and one output layer; The input layer has 14 neurons, the first hidden layer has 9 neurons, the second hidden layer has 6 neurons, and the output layer has 1 neuron.

7. A method for predicting membrane fouling rates in anaerobic membrane bioreactors, characterized in that, The method includes: Obtain the operating parameters, biomass parameters, and membrane module parameters of the anaerobic membrane bioreactor to be predicted; The operating parameters, biomass parameters, and membrane module parameters are input into the membrane fouling rate prediction model to obtain the membrane fouling rate of the anaerobic membrane bioreactor to be predicted. The membrane fouling rate prediction model is obtained based on the training method of the membrane fouling rate prediction model according to any one of claims 1-6.

8. A training device for a membrane fouling rate prediction model in an anaerobic membrane bioreactor, characterized in that, The device includes: The acquisition module is used to acquire a sample set, wherein the samples in the sample set are characterized by the operating parameters, biomass parameters, and membrane module parameters of the anaerobic membrane bioreactor, and the membrane fouling rate of the anaerobic membrane bioreactor is used as the sample label. The preprocessing module is used to preprocess the sample set to obtain a preprocessed sample set; The training module is used to train the neural network based on the preprocessed sample set to obtain a membrane fouling rate prediction model. The operating parameters include: organic load, influent chemical oxygen demand concentration, biogas recirculation rate, and hydraulic retention time; The biomass parameters include: volatile solids concentration, soluble microbial product protein concentration, soluble microbial product polysaccharide concentration, soluble microbial product protein to polysaccharide ratio, extracellular polymeric protein concentration, extracellular polymeric polysaccharide concentration, and extracellular polymeric protein to polysaccharide ratio. The membrane module parameters include: membrane pore size, membrane packing density, and membrane flux.

9. A membrane fouling rate prediction device for an anaerobic membrane bioreactor, characterized in that, The device includes: The acquisition module is used to acquire the operating parameters, biomass parameters, and membrane module parameters of the anaerobic membrane bioreactor to be predicted. The prediction module is used to input the operating parameters, the biomass parameters, and the membrane module parameters into the membrane fouling rate prediction model to obtain the membrane fouling rate of the anaerobic membrane bioreactor to be predicted; wherein the membrane fouling rate prediction model is obtained based on the training method of the membrane fouling rate prediction model according to any one of claims 1-6.

Images